diff --git a/.gitattributes b/.gitattributes index dd3131c38e4d9165ccd8ab45e0778f23e97dd585..b9f92fadc48ab29a132e2a78224b5c5d3864da44 100644 --- a/.gitattributes +++ b/.gitattributes @@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text MuCodec/reconstructed/test.wav filter=lfs diff=lfs merge=lfs -text MuCodec/test_wav/test.wav filter=lfs diff=lfs merge=lfs -text checkpoints/Qwen3-0.6B/tokenizer.json filter=lfs diff=lfs merge=lfs -text +wandb/run-20260316_191457-oo5exfjc/run-oo5exfjc.wandb filter=lfs diff=lfs merge=lfs -text diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_24_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_24_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f37622772130d99cbd60ed4c0c4ade1df0b1b13 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_24_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a19c00516e18639e3bde5ec0493a65732fbbd742d1a710b35032bba1bea38609 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_25_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_25_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ec11c78063a989dc38f96a8e65279eaf83ec14a --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_25_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19a8c9a9781ca55c8114c64a2daf4724b7032404e264dc21befd308e49a4fed +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_26_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_26_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..299cee58fb1d88aa5584c3c6b993867b1c9e4693 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_26_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae93adb3f51a886f419307f21b1f34345b237c8b3551240e59143513d98e8951 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_27_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_27_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..469f6900c73c1d7e460edc11378e6ae4e0ea52d9 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_27_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e19917175efc11d7e2e06e02a0fe23a8d2376a3283fa1f4bcb99a175b526be +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_28_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_28_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b036b0b4509c39d2d90c21dc9ccb5f75c330a426 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_28_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac2cf53322ad83badf3f5e1c1f9ea7c7b66012e5cde7d792eb5fabf17e39864b +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_29_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_29_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f0217c920530ce54b77e7a66437252cdf929fa6 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_29_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc8200334cfe3492b06776c18b55a4eafb9edafc93cad9bf5722332d4eeb2b6 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_2_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_2_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db508b4f639031d72a88082e2c05dc048060daa7 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_2_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11357c10c26e249055051bbf97aa75a653810ee109b75c9443bcbd3cd4552225 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_30_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_30_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e63327b501735682d6b70fb8ceb5ccf0a3139492 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_30_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f71745b47f0c2e02de0e7312e60463bcf529fb4be7f7af61a4af09b6dfe2dbbb +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_31_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_31_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c9cd12d62ddf9731d776f876532f9f7feadbdbd --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_31_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:730c7d559be0354996a6f05d4a1d53e18e517b55aa890c98394f63a1edb68be5 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_3_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_3_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9269ed92f24300f3baf774bd47d2cd77af110559 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_3_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:117f5f74261b5cadbee6a4d535bbadb9b0cd007ca0eb71de8210600c7bfcc603 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_4_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_4_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..03824bd548a713ee62bb030fbc9af304b247c7e5 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_4_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d442f946d76da52154cffd89a5756d3634f05bfa25a2cc8e70a95fc76734b16 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_5_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_5_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2931cfcf45e8e5801f55c18d671100963d5a923b --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_5_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b86aac563b865b022657f58e38da1a920af0f5db087d0102b7644f693acf144 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_6_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_6_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..18ec2ebe7488fa866e46382a3f5cfc2ea6952823 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_6_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaad76cdebd8a7caed8286727e39e1f3c11df9fa40a5c4ba37e9a63a3367baeb +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_7_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_7_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d07fb2550bddbdf5ffc2a6717bd968fe1eddef4e --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_7_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d66ef68e083a868e8d2cbd59b33d7f2d65bd89f35dd311184112bc2f948614d +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_8_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_8_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d0889d34f8a73a53706e9e4ca1fddd977db0d72 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_8_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3daf1962d645438d82db282e4273b31a6f15560acb8001f6daae5995a52674 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_9_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_9_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..677e86dc48b6f536018a2faf041a627f6e24b256 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9070/global_step9070/zero_pp_rank_9_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e39eda259cd33dbd5ae56ade73d828c77f0603d68108215e6b4498ab0206894 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..814e3eef413fc994fe2bb03e7d1bcbfd963687e5 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bdaff86d34dc880a594906bc4c75455357e8b67a9cb504e637d0070cf53bcf4 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aff9967d6de176e28ed38f0c53f4f43d81c5a631 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b01da34a350f47f3eb2f099cc38886a19952e3da148a46380282ab0f99e779b +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c1a956c0041a0e0891b50841678392cc80d8c7b --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:baead71e3093e69dd6b4d886f522f971f865f4debad9110500d6c7dc23543236 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c17d754430e8f54c440db220cd9cc7d37628ac5 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69427ce20c4900cefd2a558dce56f6384714a13d70059c88afa736895a98ffea +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e5b5e9b998367d8bc7aa9e200bf43fb80d8127d --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:b2a34037050845a9dbeec2a0351f07e8d901e49ab133315653b02c6b0ad7b578 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc123fd233b51425b56fa91e3942d2813c54f7e6 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:cdc7a4c4ba576329e0f144827608c272e9bb355c4017a673c1d6010bfa366120 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..65bbad1fb2fb976c4430ed4fc994b64f79541329 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5897c81d0820ef23fa309be320b04d6b619204481047c9578f44e6c3381317c4 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cac801cb989071b0669f918943701d4709a42fe5 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6ae295ee03692ea454bf27e0f408b5fbbc2de55a8b3eff3cb419e820aea6a9 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca17036b9f9d69cf43f153581e1ce5ee115476b4 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5575baf31d14acffa247888f65745bca803e27a73a5d8c189f93452fc417cbfb +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b513056f60f14d22634c7594b12e0c139c87eb2 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:283dbec2bba3e60978d5c86359eaa3a2864eca12a38c08e49da1a725f0ce74bc +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a0d0aad7ed1a64dcbdae55d82150ab7d384d781 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:d0b37f9683a113d6768c510fb5eb222b0b025be73bb9079ed59192b9b7a30179 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2aac73a2304bdfa7c82d3dad02f714dc62fb4ce6 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b76fccc3c18fe176847139377ef91bad28d8a6b80d5997f5cccabad14d4a264 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d176b5efa6905e17e831833b443220b209e2065 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b01d22c9207b5994b1e00f70c5bf525402bf9e5e618605df85c3f5da73c14ee +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7aa138f784e376b65caf2cda1334b271db113ddb --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:fbd89c238b0b005fa491b1039cead8f5c3cde3895f1f70d10e7631e76254c8b8 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad062e88aab238cd859f4848f36da99397d70239 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:ea048b15c6b2fa0a285cd63b17f375d23f8bd2f90d0048a3c71d059264d11724 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c29fb87b5fcc422a72dd3ff2d74053d5fdbb6a2 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02b9365c21312771a2780e9a3e059ca371b38b91fc64357723a44363e7bf7d19 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..011c67dc2367bd9dbeffb2f5c1b267659a8945a4 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:b80c922c207f183bc2236d9f5042d401018752a0999e84d51766c74e5d9c1942 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29186e271486b29b244c88bdc5edd85bd7236064 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6176b42736a61762e36cde84dfafa6ce8b5e845f13f29bc97aadda4adca76963 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..214dc84587d149c099e9e116611c86e57b1ee916 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:a643d861809899230505b2cb054464c45a9ac0631557dd87ab02e93841a586d7 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..198674846e745c856bcfe155704c048fc09261da --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:a4d6fde53c02ce5ad4f6d2b3a7b25caa63ce7054caecefdc34b1e972f3036f0a +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..460ceebb4a5f6b213a2582606b064284bf3cffe4 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ca46c7e96d59a429e4fc6763752be166a78ff029aa56b6b8480ce67d6d3baeb +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..073490a884a9cf963a85fb2bc9763ab15c539fea --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:dedcc225c2d999d5afdab531fee37ce0da4dcb9541eca676ce079f90831e4ce3 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b7aa399ebd38136c356700c39f8577df47fa96bf --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27bbcb54e60e294bceea90cdd4a6bcee0d31d34df550f9182fcfb949120acff2 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..978f9a995c36a9d2cbe7390fd1181972f44396a6 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba9befdb76a9dd20c015527cfed51a3adf0f519ca299c4c55e59b7bee725957 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..23b512040b61ec23fa29f8a0c4a0295e9984bc68 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e133cba93ef278edc0cf8e8134062de5d13d3a1f7ee6922e01d46bf6e172498 +size 306080081 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d049e8e7e89886c7e3859443b4c1a77eaddedf2 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:be6a403d91173b0af753f525020569729385c8fc3f8db0f1e18ce8a5011e3e73 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..28ae4266450a1305fb531edc06db951d8eb4bb5d --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e041de5dfa8b9f094a400d2e5f98556a6e37668d299bea6c82c88aea4beaef8 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..401304b16ac388633dfdda5ff9e9b32bf44e4d45 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d9d77119f5fb125d52bc55583345b41fcb2998a8a1fd120329c4e9cf34f030 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..95cc348e9c859ef727d8c7c57597de5d198011ec --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc3b18464baad050c95ead904def4de24eceead379b78173b23de5b7d27f693 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67948b710547cc3bdc30308a855e2f29e317ee00 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427e51aecf4239467e1b65d7993c64a7b106a7ef5b9dcf8c0da7d09440dbf731 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85fdb196bf71b9371f8bba09585cbe355dceb415 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/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:d29b75dd3ecb42375ab4fb7e6d7436978a88f7134ccfb9ad4649334830df4913 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac018faefb1dd4a34991922d492bbf18e7d83634 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d707556272206b70a50a03f7b6f40608034ae8852789b333b7bef87ace47a86 +size 306080069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_0_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_0_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60864604f35c23a1bce02bef4410852af86f39f9 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_0_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af085df50b7d7262e004a89c083f80e71faa6dae75d9b393b40d8794dd471b3f +size 202133 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_10_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_10_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7bfceea95e3cd166648c778206d78e56a794a6d --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_10_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c2928c88bc9e28d94116d671406283422c31c657037d82088d348894218289 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_11_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_11_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a1e9d98c3ee9ebdfddaafe592b1a8c975b5f390 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_11_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1ec6232431bf2442ea1e72df19eb66adea795241985ca2626c330e64f976b0 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_12_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_12_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5ee90554955469baf883dc175a747d8d9fd94ba --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_12_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96677975b1870dd842a9992d29bd4a86ee5bfb9524bd719fd31ae293f441cd9 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_13_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_13_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5290dd24efb28a115716f31bd5dadd39fcffa2d3 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_13_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd09d84b9750886ceea9779564333fb4a6b0f5e920ee44ac4c659a9cb9fb644 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_14_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_14_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..739cb2edb49604e3a24c81816527e4ac59d90dc6 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_14_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89804b5d3652aaf62f6d16f3069fdfdbefd2ccdcac872392d511fc8d3922f649 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_15_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_15_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..31850569cf813076b3d0080906e6a6d6865253e1 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_15_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:293c74693d7191a4f913c7914a51de8f41ad733cc2ec59626fc26dcc2528dfd4 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_16_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_16_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cfdf2ffb691425cf1a261c0746eecba5eba67ab5 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_16_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8268b0fdc3eb855d143ecbbe67fc04a425601d2b3b830533cf3d13516838f4 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_17_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_17_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..810a4a2545047992465e40bc6c5fe88f9c9979ac --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_17_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8995b5afe55d643e913af93cd6b9cd6f5583553a5b78061582d1cc2fb6095488 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_18_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_18_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ce4998a0ff80922ebde8812fac27db540dac9ba --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_18_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b6925f9a979ee8d60cce3191375aba54cd04971d5b1a8fab7ae745e046d16be +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_19_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_19_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..75bfefc95cb8b0b2cd34dced22aeb2cc7e8533a6 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_19_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:606bda373b376e386a61bd2cec76b7fc029a4092b3db8f30432fdcd66d35dbcb +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_1_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_1_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..50833e0574952a2d1e4e8996f8b9ef7c3c0ac0c5 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_1_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e1575fe3980ab62c960d0f726da19be207df100ff881336314c8ef5c0cbe2a1 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_20_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_20_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cfb4153708e582465f02006df7f0c630c2105cb7 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_20_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a8d98d463cfeae8029e7f26a967397e1034965196807e3bd3302a2d603ec5c +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_21_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_21_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1cebe584a67d806a16380d1cd023e8a785c383b1 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_21_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99caf6f204fd9a43dd5f68a902dc4790d5be907f425a81b0aa50ecde8f203b00 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_22_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_22_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3274e0dd664bb4de2fbd4b599c14b47b626cd2e1 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_22_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71736a3766ebad538addec5fe696bca41fcd8e749f3242fd30657ecad3bdda1b +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_23_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_23_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2caffe5cda21e40f2e8294a13dfce8cc09ef5850 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_23_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f1b34839404a92fecbc109f1c7fe9db660cdc12fda3f96b90041b74a010261 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_24_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_24_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87ab4b12e596f62b15dabeb03295af0bc6e7b964 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_24_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf5c22b6e59c23fc02ecb887c9d31d57d6c80a977b74224b3a2e7f4a9f03ae6 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_25_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_25_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b378ca2c79463122aa57b40a76b92daf91f1b5f --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_25_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:600eea834511cdbc98a939ebb8b41fae4f6433954aeeb35c613291beb4e9563b +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_26_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_26_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb8bb72a74ca95f67094bb3163aa7a148182a91b --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_26_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e5113074009075b3220eef03ae00f45f2eaa2a3a682864635ae0eee4125cbf +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_27_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_27_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f0899da6085564f00806a43c322f4beda337417 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_27_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d2b33fd40544bf64bb33170879ea394952c43c34fb23769aad5ef29606d6ca4 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_28_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_28_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ce2fc5003795a30637a79697fe1280152d4d29b --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_28_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f07d8a74e3fd0fcadd6c925dd3f19db3690464ffbd7f2534ed370a0235bb79a +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_29_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_29_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4cd78569409156caa6ad27ef90c245c8d78d99a --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_29_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1b67331231c644e387685517a92fc31684551858994c732d67fe272e5ff180 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_2_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_2_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3a403860079a59725a75862aed5a36d4e0f8fde8 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_2_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8efe4ac40f6fad5ea01b2b1f18e5f4b5839654a361c0af7542a1f4e0e5a15deb +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_30_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_30_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cb442793c5f2bb211e14c5912f4588fec74407ab --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_30_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036f9413dd3e29226a78a42aa08ed24e39820f0b305e59da28168650106908c5 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_31_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_31_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a400ac0349acdde407d66e941c91c039e99700e --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_31_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e30fbedf67f4040fc070781b811309581cd21ef8eb7882e38d7b64988cfd98f1 +size 202471 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_3_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_3_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7cad49fe7d49902cf703ce932ef6119293b59883 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_3_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b094cd75c580140a816ffa449011f23ade4d296fdb95931aaab06352541ab9 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_4_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_4_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5418a63c0586bcc656d28be3c01371ed2b39ac15 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_4_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a461ecfa4f901f94d762af5c1e0ae6a803d27ffdcfafa97ef39f5bdd0f06075d +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_5_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_5_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93315fbf7bc8bf30c21093936b7b5fe8df002925 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_5_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39a986ff39fbed610f5c4623ca68bbd34a1a665b70d02c64b87117d71de7c451 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_6_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_6_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1cfe86e73f52aa0ad8660a6fee28bff69046c3b8 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_6_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72bf357fbf66bd57950c8c861ddbbc4b09d00c97639e5c591e003184287e05a6 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_7_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_7_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd95277144d06d34770e4dbac61bb73b290f291c --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_7_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de6597e7bb33bbde16a24fdf44b0d3437dbfb944d84b309e010da36c8f6aa28 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_8_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_8_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f1bbf3a2bf6f86051d48ddbdda69184d2263e32 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_8_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abeb07c3b5c1a1b0b07b2599f89308f9d9c8f5bfe5d0609200f1d101e6c6f0a5 +size 202069 diff --git a/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_9_mp_rank_00_model_states.pt b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_9_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..218029fe7e581213837ee78608b8fdabba2cb573 --- /dev/null +++ b/output_qwen3_0p6b_train/checkpoint-9977/global_step9977/zero_pp_rank_9_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d19ddc115e9f1725d406dd7a840506c7e876c38f245c618906ddd6c8e3884a +size 202069 diff --git a/wandb/run-20260316_191457-oo5exfjc/run-oo5exfjc.wandb b/wandb/run-20260316_191457-oo5exfjc/run-oo5exfjc.wandb new file mode 100644 index 0000000000000000000000000000000000000000..0581585ed0b4e23388b8072a737fb694e3b70d6c --- /dev/null +++ b/wandb/run-20260316_191457-oo5exfjc/run-oo5exfjc.wandb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41a470501557274b750946d798dd8fce7d4bb79f451891c2980db1c097af43ec +size 33488896