diff --git a/.gitattributes b/.gitattributes index c3df32b27e69e048c7ca88d485dad49fc5212b4e..7a4a5d479ee55f6ff96202c11b62f95564dc42bf 100644 --- a/.gitattributes +++ b/.gitattributes @@ -34,3 +34,45 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text grpo_full_qwen2_5_3b_20251121_111716/checkpoint-768/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_layernorm_qwen2_5_1_5b_20251127_195534/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-576/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text +grpo_full_qwen2_5_3b_20251121_111716/checkpoint-704/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/tokenizer.json filter=lfs diff=lfs merge=lfs -text +dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6da2f13c47f2bb9437053575f06e96fea8dab9a --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db40403d691da552719ce2b79b9c0355e903fc67d8c1781e683cd433ff10f5fd +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6da2f13c47f2bb9437053575f06e96fea8dab9a --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db40403d691da552719ce2b79b9c0355e903fc67d8c1781e683cd433ff10f5fd +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76148478d0fdd01b07c0840ed45e764dd0b9a3c5 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4451ecb6fdb9aed646ad06e511a03a7761ef452b10174aa1cf8863c8f0a38850 +size 112744453 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..39fe3f27f2bc523c9523e130608825783ad9cd0f --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/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:d891cb9c976ce2fd919407e10ece9a76f5e2d99e384bf23edaee6d4878eb94c1 +size 112744517 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..531f33bd16b6ec862f784fcbd5bca503f5d4b1d6 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/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:f630caf6b4fa1ec40d9b3b30e670069e64ed8e82dbac9aaaea6179d315004f04 +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a359f5d62b1737ba9e7e65514f120d7b4fc5bb1 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/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:fb0f2bef89f8c563f658b755d285e9a780fab3ea7a107387f7bf7681c2bbc27a +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1147ab3a2de3c7ae90079234cb547c2bd8ef15b --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b401855f3bc14492a875840da61ea21a4f29245741cb7803bd46b8048d47581 +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3943443516616af0a7ca18cef7ce45c68249daa --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed71bac5dce1f67c459a40955b603b58b80be895aef84491c4409fbd9715d467 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..b76c14fea8a4bf9245774de675086c932fe462cb --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dfab16487f36d646fe2f59e45691854b0d0018fe602d9f3dc3e4966a8c6edce +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..77856e1a9e0672a4057c95de759f27dd9032c131 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d955d4e82f7efb3b29bb7cb54ca7b2219355d4608ad7005bf6a90f4cd6d41543 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..dc636bfb8807dedc80ed2df9de9cd06f5b88edc2 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91876a07681bf4f7fea42a0639538f8e6611cfef5918d671a0f4825e1b0a6571 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..99d91d84ee7ce6fc15f8af630d20f12aec7f58eb --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a000cffeb82f679c5eea33f850666a8c70d17499ffc7879cf41417a213f90c +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7b714318e260c2af51380eddbc374588f9bb0d1 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99b90824dc1ecd5436d28ca9b694e284ff33c3c41052cf1ce36638ee0d41fdf6 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f35ab23fa3951092b60a1a4baa0f58a3836235a --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576a9d3462c9625127950131880fc9b88ce2970ad079a0b592613b031ff7f91d +size 112744453 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e7668d5a29ffb4c2d4c40e736661f60739acd2e --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69447574dda8de8f94ee4f43bb8d3ad4e9925b81b598f0c24042f593c54c7f20 +size 112744517 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa0f5758b795d1ad8255923f866079b1145f0edb --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473d5b45c236dc5b20927999bec9cde0264774d52255aaadb822f7172cfdad24 +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..75ef67ccbc5d080bf8e876aa807a318a505d3a70 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f05d9ed26a870013bebe7c59504c5def602fc8eaef9cdd7918e8ddd4e818a06 +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f953d3b2be868918cf280ac4f832bba982528657 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:158d07fba208241c5a375f1c85c446a033a735e50743bedbbe426e5e4bec4b3d +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..534ba36bb8a1338d425eb77a16016e93b2495afb --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4698c751411732030f487754fa82c16807606ac4bf34646bce9ac035c19db48f +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba8dc8ec2be5921f5f06bb53f23aeb7a0a5f7854 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f10842b185db78db84307c9468fb15592897fe02353f4b56a8b84d8241e115 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f6187c3c4972e1ea52c8403499efae4e3eb65a7 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ce7e8a45609d7338eb32f0c379aee06f52bc86f384ec6889a076a9dc566218 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2bb5b51990180a4efdca369e08d91c674ff0388 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc51f1486d0d1c4c664a9c835cbefc63d60bbb1d6efc5c4b77ffeea27c4569bd +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d08ae64295b57090bbaa5d6676253533d838873 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72d1751ecd37a23ecd20bd8b9260f394c2f370cb5db8d203bad7d01395f4fb8 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ecba42feb0677de5f20a440146ce4ec3f54756d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52f8618019017902256bdedd7616172afa1c6cf1b2d2ebab281e06126dcb48eb +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f119ca02b0038ff74bb7df81d4276fe96324f3f --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e16c5fb3d90e6a34727a4cd574696d0a241f12f3812e44ddfb1352ef0b659f2 +size 112744453 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb65f5091921236f266e387ddb9da202d745d949 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:080e45090176cb53d408a8067e04c09e2b7a6d5e2916a3d88a496777a8091320 +size 112744517 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..97515a4069832ef5747ac03735e80931a3a5ada4 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e487af43d5fff64fbf628a4f0bc66eb19aeb38b196aba4455dfd969afd96db +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca7c4a8a814fe44e02c4c47da7dc1f820fc54b80 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/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:a0fca9e8fd4bdf420b1e4bb038f80fa8c3f419c87f5a57e11c0623914c7fd053 +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1861bb197088bad9998e77149bcc9996d0dd9f4 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d7b9e4a0462ed5b0c91fe6be60d7b687d625baebcc6374a33acb6524c39bda +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..b4c2251e02cf5dd34bebb883a003f59bd6ef1017 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8feeab9509aabeee1af85735809fdd64f7c404d1f0c8cb164b7a436250cc37 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..1e277cb757c28202cb1bdfec643793c6240fbcfc --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88698715a36bd427d7699cb5baa46eebd673d5020aa9ae5db38e65a86c02cd3d +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..768eb7e7e9ca98d9fcf5a2d82d86b034b2250946 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6835b00eb2f014a166120c342fe1acb3bdaed455209f8560cb920b823a54e2bf +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..5fc1dd4be4cc2a2cf0a1a1e8e75e260ada64f980 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57be3d3a57cd7d2bb9ce61c98f34bb71d514d7b57129ac73dbb57bcda5beb49d +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb4e8900ca74d271df161df3e78c5e3163d3ca2c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac63e93328a0491bc31c5b67747712626467b0c1fab68bd8f3a90d2ffc2d318 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acb4a3173b1009a1c39c18614ef5cd025030f547 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4149c8bba22461601a2e10093f7886e02152aaec98ebaf5892a794e5039518e9 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ba25b604d5342a8ed301c918405033afd351c80 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:286659b1f461514cbe9971ae284cf339f58edd6cff3f3b41ed4382485f6a3804 +size 112744453 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..df68a8f85cc012e30cf580d7b9e0ebf93a50b28d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a244603b2aa7f7371a671fda1084de4bdc2bf4025f8b255e4bc522dfbac8151 +size 112744517 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..49fa5f22ddc87f3a83c711a9c0fafba2cc6a7b16 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6892687e9bd290c50bc5baf41dfb61cf8ed2a61b876428d154f7022f4403ad1f +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0054153d98887478c70a5e7fa6d16fcc0cb92938 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e8aa74d51fcc2b354960ec2a1835b23dc02b7e2608f7fd3e554f5c87a05ff2 +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7d30c2c3ca07da2f52655acadfdd21930d9514c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8170770a38324a6a1c273d4d4b84067afe3b5d003a72f41619528fbeb6f63f1d +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..2c9712570e9aabad284e56d931f39bcd243a18cf --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d181eb6938f52dbedf15b1438d1675df3461cb95e799cd0465f8467508e31ea8 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..b708eb036ef7a61da25dd9e565d82d2b6c8ce75c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bab1276f3e6166e4f5785c675244a89ca0b79b10b60faedb88120effe421b7b +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..4681ba19c052dca55dfc970bd86462a1a6035f9e --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22fbb55dc032d8952ca5b09e769c5eecebcbdacded436af5286b15ca2087d54a +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..aea562898d5bd9253920e40eaa4cc518fda23b42 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395b9b47a095bb48b659a8d52b98dadcef202ef35dcdbfa5b145539995b0183d +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5da175406e5951634027623c46687436be96a222 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8495f527d2ae384d255f961a1b604892e1f5459d17e99146a7b64167ecb9365 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c0f329d2f8d358f85bbd76c2964275308667b1a --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b73c04ff1d7d8907b72de868c10ebbd9790812d8b0d9865ba943c702ba1efc2 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce53856117adb6888e61c13ddc70913a9b7bfe7e --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/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:f6a1712f196298fc3cb84131dc09f8c58a64be730fcffbebbd5ad9389f41f74b +size 112744453 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a7a12c9cb909447c85750a81e5b8ee28bc0bfdc --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/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:f5fa44f0f36340cdb99ae3cbe0576fa6ceb5ad76a5e23f7cb5531d875823d1ff +size 112744517 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6840fd6178310e8b52138f7ba1b82e2df287803c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/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:e30b0d9a46f388d0e51348e7df76dd746d47296694541129af4446b8fd2ffd18 +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b29a1aaa00329fb6072f1a689f49a60c41e3d3cb --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0afbed8d1286e6eb210d65ff1974965569324a230da5c9a3e147fdb98cc47387 +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff007fb30e7a7bb799059da6e604c352acb14a93 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/global_step320/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d88b9e3bd61b6985b5540de7d377dea5abe3a8373ac9441b30aa9acd24175a4 +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba51cff4cc6e22c028e194ab068a484160326051 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9edcf6e2eafde35768a598a4942e7fab8643ece83e8c00ed386f4d4709c3d03a +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..2536bb666d733e3a468752797dd50d782082ed44 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98035e22fc328032a4b7dd03107cc585858ce8c2ae2c5cad62595356773c01bc +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..398359a15205f2099d3332b0dd0d66faeb762e7a --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9726fc06472ecdb97705703756c34b1f7559125cde4298d3db32260068bfbb1d +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..fcf48bdc1e0e1a6932344383eccfebf1a9ea4f4f --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e36fab4e0f58559b6dbfb8c3139d69df8e0644373732d6c050e99fa2587cbc6 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b635ce1666c50e816d388484f117d6c351b92d3 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da013ae0b2b98d7666c2dc2fe7c1c09f26c72a818d58bd9b5b49a1d1f432bd5a +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4504400d801fa82ac80c52d9d3fc377e19522ad7 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d262c91709fc8511bbc11561ed943fffc77b79c8db966754d3499a5fa68c491 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d77d9a1da1d59a307d43fc2f879e893392ae828 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/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:e77a02ff06174e0dcd37c25f212cae83b600e19ea801d7953afcd1f7159f80e9 +size 112744453 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab72ccdd4226733f9a50815e5008d7a26c22546d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/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:c4ccb1e82c79739838c415fd7a090d2113ae84280c290d534dff0cc09b66ff72 +size 112744517 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e84d7c7e6fde560ac21ac820d0185d69903b1e56 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:200966d4c81393ba160ccb900093411eb386b82de96a93fc7c9991c666d12c22 +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da3421a346b02e9aa860c654d434e9ff3a2e9b8b --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/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:b8dae24e31dd15ab821874a043bfb806d106a6da6cc3b4ad3a3b6bf5d16cce1f +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6177ae3ed299e4c5862b2eb826df367a2d6a27d7 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/global_step384/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826f17eac467c509dfd54c2e984141351816885f796c24acc8e972480b421d1d +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..9dd902536da601ef7229ae0b876a5a651094e8bf --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba63c39858b048dae6936ae94762d3a478eb73636fe12d8ae858eeaa30656570 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..1e6f9aad9a4209e932787cc7274e746f81bd0a55 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce42af9685f2d42e079c20de0e3d2f0d5d81b64c008ed57cb7c4693f7122f88 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a2f8c5273bd4f430905a71001a5b4868b14bc6f --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d91c0aea184f08a55ec8834737dcdedce6c8011454940f8b3bfd63c006180a9 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..3def5d93e189fdf3a3b8398f6ab7296afae1a033 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f36a3e2a8851eea2f62bf9539495b4ae586979b5c188cb33a6d10d2e92389b87 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e35447364346dd4e48ff2912c9630fa0d550dd81 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a73b3132edc693a316dd18b0560b36c0fb0501d1030453a31a1309122a6bf7c +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..416ef3754cd8aaefd2978de5a7d3391a09422040 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f5ad60a91140ad628ba49fb94e6c475f9f3db98221b05cea0907fef8dee825c +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c15a7e752a0f1c63b5b65559f3683a74cea5792 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890e4800e4185e0b99a1fe6555556ccb9a0055125a2e40df1f9f410aa61e2778 +size 112744453 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..92284eb216b6bf3537a4f53a98566c5de9b9c340 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/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:a46c826f46b1d8abef9dc125f2a216df08f134817fb18a58f4a4655e31f7f278 +size 112744517 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a034e7a1e43e6689332b1368927dc3c38bef8a7c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/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:e4db71c413a2d27a95a1a390acd12faa6666130e5b8c00667f120bdbc8989a4a +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..555997c1fdf8b565029b266628f8b70ace124157 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6efce5bee3e915f4159272d373ce578f025a24bcc399c03a335479dc92071a +size 112744581 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd5dab5102d56e510b29cec90f6cefa096c65de2 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/global_step448/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:443fe499da8563c016127c5ab69eeb3629034a295449fd7d0bafec2d4d894ea1 +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec0f6c8be5342afc529b81dff26ec0d21f10aa70 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1daad4cab2d4a48d72e246f051e4150c6483ca784ac7e7abbf11964949c2dc +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..721b515f7af6f5be21557dbf2ff6bff2d2438ce9 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4a829f7f16a48d2044a38adfa7c981ed2a50fd3c41dc192eaa4a96eab74c1c +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..83976a1d73f74652804c9a98878aa969903d5775 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128d2cb8ecf0c76c167f6290516bbe88618915f135806541ea699efcfb623fe2 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..b828dcd1f58b0291e59b0ca5bafc2ba52ea4bd09 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf3450c056947a9fe3ec11e4fd24ff700dff845e1bb763026ba48f23ac0e2bae +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a39d5aae7a5de28bbf7c8e26531da9f7f0cda3e --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d50e6c2130ded251cbd3fb239e3a2e1e0564766292c69bfb4aa6ba0d973844 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/global_step512/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/global_step512/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bbdfce0ed6a90673c840b6bb9cf6e22c43c803d0 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/global_step512/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3150165223a35ff5736bd940fabc9f0e0dde62a4a78645e540bcf6d6122c960 +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..51caec989856fabc8ddf26b05a8c2a5365dfdce1 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295dc511df4f67fa4b2ca4bb2941bc0dfa8066e2bebacba22fde4ad851be9936 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..e0c8b3cd3c1173104fbe1fe16bdbb3a5bde90ad8 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6224a6bd7431c11ca1c5c14514fbd0494c79eb1528810d8a84347a3e8607c005 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..2d670f689919caac3d98538ea63b1c85bc7a063c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2240981517843efc77d547b61891ea5650ff3aae6419cb1ed8627368df9d76b +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..2637d54614cef4380584e57696096163437d23e4 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebaf55f471a919bde0e44cab57293d9b0464f72eb48cb9845fac7fc6a84956e +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..4800a9e5803399b265ffcab0af9c3fe980dbd948 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0e61c4f166edd4bd232bd6fbefe6d67a5b7e00cb803d1741eac9a6d2b7b6ee +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6df5b0e955a8b8285f62573c585c577d1eb15b62 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44766187bf404b823066bc83816633b06fc1a0d41a5ceaf5801168226d6499a4 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/global_step576/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/global_step576/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..592ce45b9db44215cd25a242bbc35a63d679bc54 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/global_step576/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04352596a030fb6fc80337cdf142c18c3e8b44a69a1135f3e9183e65e62d905b +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..be64cf9baee3dbac625bc3b749fde21794bd8d53 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c83857a9156798b78a32967793663769c1dff6f87d98878f483fdf23a0dd761 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..7bebe1cb319e647110f0447608aa5610b1036c74 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113be07e56c136955f8ced72dfd390897dd57350a3222d48379acbbf0a517eb3 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..81131ee54e679440079de1d15f99d795069724fd --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb52e6168acf32649ec9d33857f65155d20343cd768153bde841da1589ed5e4 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..b4cf0b9881e9ce93fd0f654ab5b953693abc7e1c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5bbb2424403181e8eb8a19897da30236496216e5177b4867d02a7a12be94e7 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..454813a4990df191f6951cdef743cc653ff31f83 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:105f4404298e62d6811a76a80078eaf19c435d835ba8926a324f78dfdc9fb5f1 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ec269faf03b21cf3f0cc135f4967edcb18a75ab --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b047048ccd5836a918339dff60835f9e779b278793fb65c251bfeb26a0a4e262 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/global_step64/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/global_step64/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0672b8ce54646324103935ca32b86a459a2134d4 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/global_step64/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbfb33d54e481ab5e222c45c209c9d4fa2da41cba916d320f770315f961d0dfe +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..47f92e3a351f414e3d699ff2f5baf74b417649fa --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f424810510937b6293c374c1bff6f6630a223ab489651a74e079cbe088a40a2c +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..408b3d9154484bc63fe52f127dd61fcaaef45f14 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccd28f59427338700d70efd00525235bd68695dfe317a41abc984a4ce0c37af8 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d966db269e0fa23363454583f72807ea42cdb22 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c00bd4e88dc8e9ccfe819a8ac980bd09e3d0d0dcb639d7c7661f5278f0f8f3 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6b2f34d63f41e4bc696f58403556927357013ea --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b19f0704ee8725d0c19c76d7ee9b288b8f353c64c92e1558b38563191643bf0 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f18e6fbca95d9546e2f67129f5c8f7ba7da9e16 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93cefd10607223128e502b13dda034a13939769cee1c2b5c47751dc1ef0425c6 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e127b08b795ff6c0eb819aa305a39e78780aad0 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:749d9587c20a38a47bb33be326e6b4bbcc3851d2b27d9f2f8d90fed3170fee55 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/global_step640/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/global_step640/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ed378274c12675192fe02872a99e7e7c150e52b9 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/global_step640/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce188c543bab94a2db5ad85142c0b9d2d8a391e3a05dbda4798f19fe182f3a8 +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..bfe4beb6d739a40d35505446b83b74cb6be89cc4 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b52cfcf959bf3d25df90bf3dbb4c1fab471287b782b489ebbaa5a1bca2795be3 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a815c051d64760798867f1d0a36b40da377ffd2 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2defe41047ddd94f492d64b963aee425fd9d25b33facbfdeb6d7d482aabf1156 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..577337e1ea9b00370c4978d8ae0cb8a71f2fb3dc --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95238c8315b1ff54b7809d7dc04be6ffd68c0a0b133e478708f7cbec96c1a774 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..f51bb3a22dce745ced0c1ccc0684326d4026f851 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20376d2f118209d48751225c59947179aa8a4ab1e4e1d3b674bd4cc4bbd6c4d8 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce72654f572f2506f27160b816a295cb0b390c16 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a218931437f4ccf43b090350bb40ee3df136a61635dc16c5ca38673a829c2bdb +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a84a43284f67e529c8dac439b7928690f73966d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a029e6f2f8a4ada87347dee31f148a381d2c2cef3b415de9721f99c231c6145 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/global_step704/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/global_step704/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c87203afcbcd37585fb73f184c2bce3e3bfcf5b1 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/global_step704/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ee9e144e9b6326b72cac37139b5a134e65abf8f6ffdc8975ce58d2e5cd1dcb +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..7d63a71100fa21e4143822237432fdf48b9e07ed --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2283b7d6bb081ea0bedadc3336ce735e287de2eb3ec8a08ab6440469c8879948 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..55804fd369729025647e56c78922341e6a97d260 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2757fbc4f40677f9a5df20dd0f092153fec69a896bfc8a362b545de7bc182ce1 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..f09a7971211e326e69eaecfa8c01d0ae1d317fc9 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0b951cf0a5c066b34d50a14e20c1bfc555a22148061f625422518ecac84eb62 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..33435be7e787c7ecbf3e9a3a7288d5c0f32036ce --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc030ee4b8030a7da065d31ba59c98020de9617cc3d9c75b66b83dfeed46946c +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fed940bed83776fee227b5936c168e6282b54594 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11998cc5f35748b7722fb0b2c7a077a4a3e3b00ac72b4ef20efa3259e7892c63 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..677a65d67456b92c0756c12d3ba45335ed507b64 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15c8345e8eba5393df7d76782ee4ae1d4f16a94be8ce65ac0515b59cc7d8dd7 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/global_step768/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/global_step768/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85a58f85b8ea8a73233c00fa35efa40885fcae2b --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/global_step768/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac49cd86c62884dfe2115711b87116c5a8238715361975aae57ecdb99bb9252c +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b01406f2d1e8b374a97c70e0069cf9ca5840c77 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:565fd4e8659ff2c6b8aab3234d7dd203e287c1dc8f11201ce347d1dada2cea42 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c2ed48c09feb488bf49c47e8b3112f18bd6dfe0 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f434eb1c3cd637da44bc37bfda3ba26a49d1b082cc26980fbbabc18a97a5ffbe +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..1b24f827f0ef1dcffc89206d6a04465e8835f4e7 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a3f592614fc1879917247e50bc285914e4d908fe60a573d4d090fc0012a9d4 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..672341e66ecf67bc607cbd833145b873f2a966b2 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e7b6d188610f77ff1b009bb57eda14b813314a79c28e7fa314b49528a4d660 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba0371866ff4c56375788d8e6b6ac204eca2f3b8 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c26f336522cb69594b3952d10c9ee7899a17aa4a8eeeb9d1b384b971fa4c183 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa92cdcb6938a07b2c7cb506953d083862bb4ebc --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072290d8fcd8655056bc9028c02ff129bf3232dcb986bc44a9326fc6af5611d1 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/global_step832/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/global_step832/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1928ff3ce24147e3e2662a5323c7dc99765988c5 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/global_step832/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1a671603744ea5952cde8f170f6af91a488e5b0d5bcbcafe4cbc9f85843ded5 +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab967704bf300698b27eb27f60ce07dbc2d6b882 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15af65b70ba04782ffa5fdee4b81abca30a18af9ead6ccb3bf197da5e2640416 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..78a39c793a4950a054f9fb86693e1e9665d9a4cc --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa74afdfa0b5c1ceb966b83b7d98a5a2a64ab2edb083dbcc8bdec6dde36e7cc +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ebca0423f45ac48d5972f67756c4859e50a406e --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ecd6e2fdfa006a432a1eb5d6a2434e7c36255e34a572e979d65b2d3f3fbff7 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6a4857a1be36220bec92fbde9ea9fc859ab3d7a --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d3a161ea6fcfb3281993c24cd60750cad7b2c1d6281eee365870afd7e1b289 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..8718467d126ce6bdbd53d0dbdd54da4de1ff11bf --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d2ef8130fc98df19a3863a629f0a8a22986faed3b54d90a56462143208d671 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96db417ffe5a89d79fc7908af2394072473aa98a --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89497aeb9e29998674c71a54b87a881528c17aebaa762cc82ec9e796fe2b7136 +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..fca2d18477239ba2de80a339bf41bc15cb4fd258 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a6363b8e83baea7a284c4b77c0d48f5031fa253c09de2ee92f8e56307d517a +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..1eee402fb7afbe1a5ca37a7839da4808758e507b --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:684ad310f9913bf44fcb2a33f5a16919629b208eef5df5d9431f382afd07d0d3 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea6c2ed879b3d575fed1eb5b0dbf55e92bf15fb9 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3870c8d0704b2bb736c191bff5878bffff6efc4595cb13b5e08f143f7802f304 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..3c36ccdb4c5648c57d4ab0b89a7b7a5e9c1d3da6 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f309bfdebc5f499793311884f16f97bac225110c3ed251d9fa2929ebe256242 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b4ecb0ccba616e482f4a3ec4b8e0a53368e6fbf --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfb7bfa2c34c711580edf233de0f324b5ef962a780aa91f27b4eb576e2588ab +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/adapter_model.safetensors b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e329af11a1e69985d3c1c1158bf50ff84f49c68d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3991e308032d37f6380f7236a4324e08465eb9ee983766923d2e1ee8adce43ec +size 75228904 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/global_step960/mp_rank_00_model_states.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/global_step960/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..43570691841e1ba622dcc7ff61d28def4b3f59ae --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/global_step960/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f6155f9efa04580b8b7d3b4e88bb68a43bbb2ce1dcb3964232c3f217ac7a39 +size 75529433 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_0.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd98383a442315bdacaa18982d59b94a3b3a358b --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e849b7740442edd8c1de59b396b80b394f791074d654bdad728e8cf3b391784 +size 15365 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_1.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..dbd9a4fcfa912e9986bae40ad3458d1f66026d16 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d08ea18a300ae46d6ba69e552583b52fbc8db03420998a695708098bc41b52 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_2.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..8b45bc92d124b8960cc96f1753f43e358c6fd17e --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7717366fd90c3639fc929c0c9e2181e4348f2000588c4acd96979c4dbf0c94 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_3.pth b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..025c321177ec70cd90d7100fe9710278b07e8032 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e4d4f0f2fefda1e7c95b5217f05bbd6c662ae4228884c6f7747d21812b1020 +size 15429 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/scheduler.pt b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9eb04204506c94bd661dad83fc4b7f80d132d458 --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0745cbdd2c0a3caae7131e38e031d01350e2e6b8404ec309e908eeec7592a96 +size 1465 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/tokenizer.json b/dapo_dora_qwen2_5_1_5b_20251126_115730/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_dora_qwen2_5_1_5b_20251126_115730/training_args.bin b/dapo_dora_qwen2_5_1_5b_20251126_115730/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a9f37fedfb6b57bbe9ef52816f1eb554694801d --- /dev/null +++ b/dapo_dora_qwen2_5_1_5b_20251126_115730/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/adapter_model.safetensors b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dd1e0ea51e66352dbe7835af7d53ae479ea2e04f --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60adeea85b30543a79cfc809c3e8f2b9eda7d88111eba2361e9d3920c70a421a +size 49582616 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab007620b6ecf9a3789cbc9d64170a4e4995c7e2 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4658969a01ff023ea2eb45abe4ddfb56a6d7037217ad0484f154943847f13bf9 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1410de35294187ebc205d0e26df32a1775c33c5 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af3793d3991c28920e1f3e1fe48f0c74db22f404f5f8c959d90addc81de674e +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e15fc6db002eefc5abcc40f2c83e78fdd792d862 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f56526400598435fe5fd11e177b479d8135947bd3371243e5bd3721dc5e962 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..96b94f2b5e4134199fb51fe5b34d16b23a6fbead --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/global_step1024/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2943a972c8a303b0a02a7a7e70da506c1fd14937370b30c650e3f25a4a28c340 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..b5ac6be1c3b3e675a2447ec88d2cadf188ea9496 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc2135a26cf2123f5852940063a0f6d8f2fea24355f3281f5a39fe79c7ad192 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..b08d28ea2ebdcce732f2250892a691babed5adca --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e1bafd48d9548f8299f27ab4b5a53b7b2d829a99a8855c944b3959b6563a1f +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..f082e0d44723eac05f2b1e11238450071ac2d145 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3178a2e75b4a079f2e027b91d4126898c5e51928d665d6a225e41472e778fe68 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..88e8a30085f9f90ab03e6cde0d5a8f7557742e2f --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f350b82cd9760395cbedf072b8c681b7b2e0fec94dcf3fafb2a53bfd489134 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..99d91d84ee7ce6fc15f8af630d20f12aec7f58eb --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a000cffeb82f679c5eea33f850666a8c70d17499ffc7879cf41417a213f90c +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..74ac1b73589f1e6f6e46559f6e439947f2da6cba --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:518d7143c744796426b998ca6386e53678787127fd3c856c0bf838c385d9fef4 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..611079c015a5877639ec1a57ad3777dd646bfd4c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31bcb1acbeaa649bcc3c47151505f7a2257e8fcf91f6ef0c90ad60c2b0365bfa +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa7ec8d0be48bc228917bbe94607620c07533e03 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/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:b0dba6a8be0b0ca52dcbb059dcad3ca869bfca93db6238df16c253b57b6d13ec +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..12f620dd8fa5bd23a994698f606c9b7de129988a --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d301eaf2bb9887d58316ad8d0b61bcaed718debc5443dc7e14fe00c10383dfa +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..868727751c07aae526ef1d07286c4d6a9f167e00 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcbffa064d1191154e5b4c39a1d37b3dd267bab7c93ff888f1eb776c0922b199 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..66e112797630fec1fd9f2d856fde8e700fed145e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b09be62c6d8a5fb24822fa8037f14266cc876e9794ad0c8c0c4b4967bcbc902f +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..780eaf61fd941c530b6e4b6fcd144264e8539c3e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dafabeec3e7fdc20a952576340d0fa8e9ae680f3997d1690ce20fd340d56b2d0 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..2812dad39f80c82fab0337e65823452e198dfb3a --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e80d42f2b21c37865ae54bd694da2415361abe3f94822cb6275d030054c9ad +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d08ae64295b57090bbaa5d6676253533d838873 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72d1751ecd37a23ecd20bd8b9260f394c2f370cb5db8d203bad7d01395f4fb8 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d43040939c4fb3c082e53ecaf7d3c1d5c2b3f0db --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/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:c7ba7da74ecc3eb7a2dfffc90f48b8ef71d47801612cbb81c4b52229d0e19af5 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..217b6ff0ff8d3cf132f3bb7edf281b6d3bd1235e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cbf457283e7e3d743f5683f7936f4b669b7497a7f9465bfa2b5a61b69eaeccd +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa35bfae2354ce5e7158f0afd4e6da25221d78e3 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a4d2934b21566d7334b3364114c341f300a6293b7acc0c331e177b593038093 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d224f0c98dd2c96505c3346421e5c120c91d180 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f07e61212013dbc2cfbce66c1203438b6033643bc0d866578aff48f634790c2 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/mp_rank_00_model_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9645d7acb25ae0bde5130b226403ffc24837baef --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/global_step192/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eefb55e724abad141e029289b5a7098cd1d9350a2da60b148f513d56355d1ad6 +size 49768921 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..9de77bc507d4832d3efec59e5f7997471279555a --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce9c5b336b6f56929be1673c167b76b030866bc5ce1d6401469078a12ff490a +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f09e06b4d492619bfe6a14e90c8f395d13b200e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb4946b33b73ef77834f15d124e1171d560858cc986e0014c847ec5526f8e55 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..421619d090efa7e3083c49c588fb152ac7553d2a --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9982201381b5575e84f44217c87b79204e136f4c7ab838f74814078f604ebc09 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b836cfb7fcaf0e35933648468b09a3c9f6c5bde --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ccb804be449f3fe9d1ae92ced956168d1cbfbde90f22cbf1c09ea053a88fb97 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb4e8900ca74d271df161df3e78c5e3163d3ca2c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac63e93328a0491bc31c5b67747712626467b0c1fab68bd8f3a90d2ffc2d318 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ad58cefac32ee056dfda4a31dd1de0f8a5f4a0e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67575dcb09a140b1cd5428bb2f071e9512b1042ed2800d5b171da2931fce1105 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3033af6805ea22d606c7780d1b671a9cc92f1811 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec93bc8928d5651ad23cda906174e3c27431eec556799c32e905c3ae6d35c4e +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..823ee09bdbadff1db50d418eb12e5d5d85bbee2f --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eff49186df252e32125681ac72f31df852614a033708293788e19fdfb366dbc +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6971c7b7e8eb07faab028c0db2f3445824a3efb7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e207c91a79cb8c67f9c997fa695019b8761c0e5a6aa8c709772a8e13a0e322a +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..08f2a492e05fba949477c34b27f12b2b0f5227d2 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82dc46da6863e2cc61307ac99ba9ce6bf452e9b5ba498441dfb8bb6a9e2704d9 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..96705e8ed5bc064d2097f3437d5ab82635cdc654 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cccabaec95761e37f492cbadd602bb38abc8d09f3d15eec6c4a6b7802e0323f4 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..629d514fb9c42ce0d78e98ffe993bc38ab965681 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5701c950a9cab62cd70d4a275c15e4486f2ad12e0eb69edc0003df792da8bc36 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec95dd8b7088b135693f2e8a645ad4523c9cd971 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02d1aa4a1c20fbfbc9e0643ee66626e41d30ea55d50f1f19c7e09d22616464d +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5da175406e5951634027623c46687436be96a222 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8495f527d2ae384d255f961a1b604892e1f5459d17e99146a7b64167ecb9365 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d6fd67bd628622a0c62161573940cda62b9af19 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b363004b09c31dd6498a86312816ee5fe6f9874a0c2254c81be86682952252 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..95977316028446e96292132b7b87d633cec57ed0 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/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:ee38bc21d6758786d3a1539f01237f0c2b0ffbfd13020ce9e78629d815a2b96f +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8af45c1168b78fff21de67aeb5fe3e6c8351239 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01970199a7011b3a7096e3bab1c5c5a3df8f091f0cd019012e49e37e1717661a +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2695312d47b50ff281deee3a0113860ea51a32e4 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/global_step320/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:d180d547ffdb2d811b0ef68c25afca8a54fd8050fb7de6ca4b2238ae9eaca17d +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e7810ad5e09b4ac363d5044482ca481f2b460cd --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6671a932ef165dcc451c28df549f51e10a2a33a353723c0c61272055f82cff17 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb5ccd73a1a0d93fa034e9f6449735e72e0de7b3 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752ce0a3c5a067c840af00fb8855956e89db5261e8bf47e21e883e765ddd852d +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d02acc24b3d1c73b91c16acd7b67c977606a41d4 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14368b91924e67ec742409eb5636f1ce009586561a35d02b7f9e93965c10bb88 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1ef8be139891d869a07545807f754f9379414fe --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:240f193d6e37d42c7d62917cc03fbce53a967edd2939c9062eb41389e0b367e9 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b635ce1666c50e816d388484f117d6c351b92d3 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da013ae0b2b98d7666c2dc2fe7c1c09f26c72a818d58bd9b5b49a1d1f432bd5a +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc6c8584695fffce50aef16c2376c0ec9f9418df --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/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:f9733eea15676ba57a161353c4facf0a185f779f935a6e736bbc1a20b3302be2 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..575e1a92fbf629fefe80b305f6ed5787605fd6b0 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7561ffad892a48d40848971a75a0acc69147368c659ffd1fc073b61a15322d3f +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5fed2b15821ef6f1f8e71fb1a5ebc689c2e441f5 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98dba9ba00f49407f731dd9f1590b1ddddbaf4aa58bac87d29964426528d0aa1 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3914cb02c91acbd4598daee03506dbcd722d27c2 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/global_step384/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0f1af2825e9ed1ca3effc3455d5b0b9319f619c2dd7f6243315c82e547692c +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e6b3b217e321fcf2df5bbe38225247eb0b47aa6 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff584d64d6abc46853e45d41042fd36446c35ce7b2d8d7c3574a3aac48d0f058 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..920a7d4b22044212451e26025f611bf3b077e261 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef0ca383da0b3944f25c29cf6262a61d04b3beb836686975ce7b7eb3972db5b +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..e704879831548a0e6e0c8f7ffeb9d89b399e91eb --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48f2eb0abb4c959ce934dd2fac9674b0c4d3612ff232f6a7489efcdc1eb66e99 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab713d8ffedeec5545a6579409a948a2aa6090e9 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:639c28c8cc4aa6bb9402d161f79ac5275baec5356db8e76a9dec62b7c1c5af84 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e35447364346dd4e48ff2912c9630fa0d550dd81 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a73b3132edc693a316dd18b0560b36c0fb0501d1030453a31a1309122a6bf7c +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..19503c397f99b739b6c4690b15b978cd1e818a8b --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0200f64371d9da3c6e0b6511963bf5e97528dce296634efd8e7aeffa740669c1 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c13b5992cf28ef81148335221174538c7eacfce5 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/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:b6d887d7c0c7c01f3f23b9acd307519e01dcfb585260f671c3a5c2209f4da5f7 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7ae371a0cc4d65a4eb815e16372a3f948512594 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/global_step448/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4187c59e37ce1b986c72c7bb03de7f5f1a4b1d88a8ae247723b44b44834ce508 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..08a82837af84b6824409f751a7343d7b4d70a9d7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e07ac4825188b244f99f5b238d2bc545ca4743d75cbc15b0bf5bde8277027de2 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a6e5999946bfb9f7a8e8da54295ffb52c40a2ac --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d2970876c547f7ce03d3492bcd85a481b315cd4dfe4f2c9feff2fe2684577f2 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..69bb76d6431f2eb2c200f07991d00bc436c0274f --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72abfa570d36436e853583ecce4243d7c3830ffc1407766ea3a8ccf8cb5f33a +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..125aa48b73fb9303a003b184e6d314fe1ea5ed42 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46e000702eaca144310b08cfb629aa5bf708c9de067ccd3ab356bb20ba258dc +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a39d5aae7a5de28bbf7c8e26531da9f7f0cda3e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d50e6c2130ded251cbd3fb239e3a2e1e0564766292c69bfb4aa6ba0d973844 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f129199fb64f193d21102e1c4da57459f38e478c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/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:ab4d1abbb69fcb876895d8be17859530d521cdef21b252c4309fae8ffb250257 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a753b8c577bc3a0db886a8cbb2aa67442e0737f5 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea44d4d3e5e141346025a976feaae71a49ab288b6b2937e73c50584921b1c26 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38b2f91424f4d4d5a1fb8df39b251a5633b18fc0 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da743d17b95601de01f516975d9ea6176394d4286856d4937570291c2376dfa +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c11fff63fdb1ad9da99af4b8bfd0759c641a0598 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/global_step512/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492646350cbef4b3f948636fc73d922b364364594ce1457728ef546ae4866664 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..34d38b3fabbd9f05a2c44a4da7817df0c8a31498 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c27303d3e4070c0e2e019d0daeb7798c96459cf77255cc407f6d43693c062d3 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..185f6715883cf5772418ffc228191c15812bb9b5 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26c6e5e6cef3b962a12523254473a7eadc680888532d2022c8fbc0d6f76a049 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..1173baf6ae6263c7146316d51bfbfa6298d7a63c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe198216f71c03c5f74286e9bad698d789df7f121552635341392538fb9b6c1 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..43a0f5d0e6b485568139d0980b5346dcb24b7eb5 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5442dd09535ce377a888b8ddcafece6bbd7d3aa8fe2d75cdc163656cd9a2f8 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..4800a9e5803399b265ffcab0af9c3fe980dbd948 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0e61c4f166edd4bd232bd6fbefe6d67a5b7e00cb803d1741eac9a6d2b7b6ee +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..14603d6c4de48c96072701faab38f04b266d352e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b1970c1d67f487a8df98b9deeb3bee979df64fdf937ec2f9f7b4cf71d493bd +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3a14b1a478d335650617cf71ee6ff4f37fd42cb --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d87f3b448d1c62f287db51d0b526e2d5126c9736d725ec2b46a816ad0702237 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f2edde3d94f96bf5eedf568e51a6eef1ec4e599 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b0e50bc1bb8dd8d77327aec6b108293356c1dda934ed699d98310b22fcafeaf +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0438686e273951b3a171b09ec940816420f6afdc --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/global_step576/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75093b06536d47975640588dd5efe846f9ac8ab5a37000b750f9711b9695abca +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..58419a441fa626f6fee91257934f823ab9839ad4 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01bb2d6b663c28f64269a7bcc2da9cb746bcd55ab78913d395fafa818f968b5 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c6b3f6645576e6a86fb26adcd06116df366b6c2 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:795ba6e9f5ffcdb33d0d938551e705007b50bb8ef68379c4cc5b5b3ff8a5315d +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..6869ac14259ec46286bdf877f0686abea23bc77c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4617f823873e1c8ffc4cb2636db66ae0a6253d89667384fd2407e1c6bd6651ec +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..aade3e3f89e06e665ca40a670bb530b9521eb8fd --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb92245249ca7094c68efaaafd897e43470d4708adbacd1ef5c06688dd483bf +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..454813a4990df191f6951cdef743cc653ff31f83 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:105f4404298e62d6811a76a80078eaf19c435d835ba8926a324f78dfdc9fb5f1 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..13cef535db92bcbcb03a6539c8f379c97d645b54 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e1735bd92ee0aef0d29f6067dbf96c82a292a5cf8eee630d7c7b9661cdb90c +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc4fd6fa089f5bd620a62c59837959a9d6d87161 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/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:da552312ac50301b581299ae00062eb2060df48593b0ef55da6ce6c6cd5c3ba0 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..92d139b7c9e4e3eb2886b39ed98b2e13dfe2add5 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/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:ebf4cc54a95b34339013e38b2957940348b479842459e1e88a2147ed7ad18743 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2923120bf2a8bac5f1dff564ed01f8b15ea0b4fd --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/global_step64/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37dacb5b0c3f4c14c474df9ebc3ff3a5cf26bf92292257f3420f3b5387e96c1e +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..6dd485756cf6fe6a50c11eaa925cfba824ef5f80 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da30a8fb1b3564d519fec7e4763114d1b44fecd75e70007861dcd18d146d5727 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..bc4cb6f7a2319388380da0806d26eeae4bbdfa1e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c97e625ef231d66d6c0382b2a61c904e04b009314557ed20b966dc6de65461cc +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..c94abf93819a051e80b7d8d39a91042589380f31 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da5d8d42118df306fd5389f12ed23619ae25ec23dd8a88cd1faeb64d91eaec04 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4aea866a0216a80fab2413a32e9018d28fdff8b --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d718a7b46f146a94d6149a4c7db35e2facc3147ad27a0c6ebf2cce0ab0427fe +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f18e6fbca95d9546e2f67129f5c8f7ba7da9e16 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93cefd10607223128e502b13dda034a13939769cee1c2b5c47751dc1ef0425c6 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..559a7fc0c3f8a002e94454b1e8facc8fe1030ff9 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2928844688872fb618c9f3fd66ff31f3b0761cc6297badc43074adafc57512e5 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35a31b951db0f2972f15ee41eb892ea0ec97b797 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:684ae1c68b9e468bb22c67c34857846e128563bf5b3b92551bd92ff4ea0f3e65 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2588161ddeebe0fc626443d12f442f06d8685b09 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25875eb05a67c200291de54e62118a0bb7523da4c5825aa1215380f18d1543b3 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b0d4130b5a592acb8238f65ed15ad3a8808e9ee --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/global_step640/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0319b4ca0c67d1dd82dd9a87b0e962df87b0b83af8779436891f15673e5d4b1d +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..03f3323fca92ee2bf25dc0425225bbf684425016 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378cb308986cdc2984bfe0c4d45888ce8593a5c65993fc1f2c49e8678598b348 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7bfbdd6ec80599d5887b35ae51421886baa1492 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45c693c3b4d1a3212c5cc37d93ea8db634e0a48bfafe93329942817ab6902b26 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..11db9169af01419972d838a0cb23fbb0478b1810 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e83cd67af845a62d4a2aa4b11743432622aa468690754297706be5e02bfeba08 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3acb246f297f078b057cb597556549c079b53a1 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9cedac4b3092ca60ef4d17205ef71881ff41f6a9e3e82467b8419d4d6333b0f +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce72654f572f2506f27160b816a295cb0b390c16 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a218931437f4ccf43b090350bb40ee3df136a61635dc16c5ca38673a829c2bdb +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..af3bb60d909c4874fc0c56fccc75de16d4a48db7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e59b8706b77dc2ef73abaad92d935b284825786a47520a8741ca3320a130b32 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9f57527b02875f69a373158e8df841fd7c3b23d --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1791ff3d8aef91f487344f7efe1c9ce99b4b1b67192e71ca0a8ec8d4f1809335 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2a147d8ce1ad39738d530cb9e8948baa77e0a44 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/global_step704/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f230153b12041fe02d092d1eb82b8421522099b4a233f4241494ce349bcd924 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..b4ab6955e57f424f2ce6c2047606a440585c4851 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6e8cb8311e1001012015c3d7e3c2f8efbb8f37417bac0bb548aec733ff84aa +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa7e1afa89ebc076d6017fac34065775272cffec --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be06066409127f3f86d152be69e0c7a60bcec6e4a55fe00415553cd53a197cff +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..81ca3a9b383c1eafa8f06a4bf6f73cb8e42f0c19 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feced724435d27be30a30cd621d464f75fd1933a0f9e267b4ee0ab628bdf1acf +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a6ab51768a563e484873ef7343487680ef7a61b --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc50310e7bd53448daf3a5c5db3acd686c218e4b84bc1d0cce03650870db14a3 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fed940bed83776fee227b5936c168e6282b54594 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11998cc5f35748b7722fb0b2c7a077a4a3e3b00ac72b4ef20efa3259e7892c63 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/global_step768/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/global_step768/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..53143cafbb12384a85e374293a4e839b7f2b3a9d --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/global_step768/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:a4354b0ae72f7faa7855a5b8d91d64f595a4cabc5b056da357f46ae76fc40f70 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..b39fc512dbae8536be75a25a54cd036da6c5017a --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c71fdd1e25f310433efb969817c7e6f694976234fce1ff019908a20e57b89161 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d2b8709ce3058fb65bd6d3fe888ef8ae78a753e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2836e9d6c41a03b1f3551f929bb62343436e18cb27550465e995752103138e90 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..5dadaa2f6f98084556b92329c1bb971ef40876eb --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7a955ec23c05b1a8e13a1ec7bc6384a90c7ec6705f6de039c97f3835ce3cf0 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..8637ad8070815480f31a6593def0e5392b4911d4 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b6995aa0c51918d1ab24db0e57e079711250fa0a66fc0f6936db4b1d5627e4 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba0371866ff4c56375788d8e6b6ac204eca2f3b8 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c26f336522cb69594b3952d10c9ee7899a17aa4a8eeeb9d1b384b971fa4c183 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..03a28f5d42109ca4c3394bd23fe8353534db0f03 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66fe7e7a0cd16456ce70ac3e7bacd3da51be63a16555da167c85cc1297594093 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..024d76244c3046bb4e9fd3b0cb232a42a9c1bc9e --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/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:f8999ae9e60936e16e351eb4c504ba613823e0131855d2b18bc85ad6f2be0d62 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..09163692a0f4e5490dbd4ae98bca93b78fce65af --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c6d5f443acae8cbbe3cb15db46b8e6db56511162e1949daf631a67ee64a504 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..87d079051ecdf1ac307b605313944b1fe40a34ce --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/global_step832/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20bf5fd0c37cb54ce478c575a1be08b2ed5b9ba22df3b60abddb6de67b0eb233 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..7de559682c993649b5eb2a00cee1ddfd08bb076a --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b46c46225c466031f08bcf7521b1447f76cb6b9d1b90c7c07bd6b54c45bb371 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..9599159d82f8221ad8dc9fd3670db1655fc2d404 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011cce0384c092f689f06adbae54bb72be3dee972d6281e3c84551cc5479f93c +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..a00d500db6cc4268cbd2c14c3499122e93680cc9 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f16b32a41f9f6202bae30253858dfd896bbe493a26d8400e9c2adfdd293179e2 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b765edd847c0fa50296bca27b2ed06d275a1ce5 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddfc0b82afdfb5c7ea91085dba3b1b344efc9685252ebfff2387bf4cd2e22ef5 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..8718467d126ce6bdbd53d0dbdd54da4de1ff11bf --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d2ef8130fc98df19a3863a629f0a8a22986faed3b54d90a56462143208d671 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6b2857d477eb0454ab7def5d979eab954219d80 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed7747b5d43c7e94263ae59a5abbb7d81279f9ae518d56e5f0cdf83d104acb8 +size 74329221 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..22fe4b4f3af019193646ecf9285af7d39925607d --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/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:cd21e14b3f3713c33061af4b01ef3cdb56d2db781cfb43051460c6fa96eaaad0 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..54a7bf647c277e8a29f7ae96d9c6335ca38fb3b8 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/global_step896/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566414b1a42b525cd6770b37ab467a2beca4baed376b49c89d1907f2b61ef349 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..6cd2b15c50def17f81cc0c81c614d46f4914e19a --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221eef41da5f8a6dc9f4278f19715af81c20a5d50552b7a9933a5827329ae16a +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..1463e3e0889580efaa4e9be734dba0847441dbc6 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f03bf8eeb95a684f6b3e3ed8cb698137e409801a2bf82cd4578f38639596ccd +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..3fda8e40059c9de78ab9861628b6df8036b12969 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570fd6425529c5ca19035b08adcfc279d58278bdfefa519ca77178f07fb05c6a +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..7533382b006a46bcb68285dd4d496e9bad23aeab --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8258fd7474f1618ddff4ab36d22dd165a297c7e7f7cc23dd39ccd377f4ac7113 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b4ecb0ccba616e482f4a3ec4b8e0a53368e6fbf --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfb7bfa2c34c711580edf233de0f324b5ef962a780aa91f27b4eb576e2588ab +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/global_step960/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/global_step960/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..02b94252390cf24c67acdd7a6056656d5366e636 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/global_step960/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86e5fab09d00d573d078f2366179aa18dce695cc86821a7ea543bec4ebb45d8a +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/global_step960/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/global_step960/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f39089896bb30a2f6415573b272c7e07bc337b18 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/global_step960/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:a5bb386afcf19e05629ce4682b2497a5e11b327f7c59119dedea8e6bc2226e16 +size 74329285 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_0.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..9805f9d9fd56f180f8bdeb6baeb3392c008a13fd --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0645e6ab28215cfd987a40f6a360c1442e334cc74e9d2ce9e7c45814f76c9fe7 +size 15365 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_1.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..519c50d02ff21e65ec037c2b94c300c23071b7cf --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ce615b866ada4d2375bdd2b4aa6ea3f09da4fc05cd94be29579a3498e2a1ad +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_2.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b22efaf1ce3242ea9c6d94d88bd90c58c7a9473 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df2562b82eff2d10c186172519688c17586d0fee34bb75ba5fcbe5865d564fe +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_3.pth b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..2cd1c76c10b7f5ca4c88885060d4bcde935d8b38 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc3918185aa53c001520d8cf2591a2e50a9099a9c88823362f42fc3f25df7f1 +size 15429 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/scheduler.pt b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9eb04204506c94bd661dad83fc4b7f80d132d458 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0745cbdd2c0a3caae7131e38e031d01350e2e6b8404ec309e908eeec7592a96 +size 1465 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/tokenizer.json b/dapo_ia3_qwen2_5_1_5b_20251128_120647/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_ia3_qwen2_5_1_5b_20251128_120647/training_args.bin b/dapo_ia3_qwen2_5_1_5b_20251128_120647/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..159c682aaa318e7275c24bd1f02a188a89b6ccf7 --- /dev/null +++ b/dapo_ia3_qwen2_5_1_5b_20251128_120647/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea281ce2c3508bb820b06e509506ec043b64d16b767d16efdd36ca003448012 +size 8849 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..542aa0de3bf8a4ae242206a603819b9be5bd4ab9 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f09fcbd1afd3dc0c1c8f9dbc04e0fbfb50841e9fd563313cb8322856b2a8493 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..542aa0de3bf8a4ae242206a603819b9be5bd4ab9 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f09fcbd1afd3dc0c1c8f9dbc04e0fbfb50841e9fd563313cb8322856b2a8493 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..312e6e64c9fb83e2a5de9e21a6f57e4e1e332c73 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9647f7b2ca98dcd05d04ed0c3a005edc20abfeaf62e278161f85c2d414d99c +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f61ca500e7880356dedbdbf94f868281ccd75d6 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b274bae2d4073226ffaf2d9e9c98b662ba40e96d3fcbd038fce351159c7c45 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f73ed2abf40a56d6b0151b609ed7d585a02f713 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:023163bfc2037e08b7b2361f0902ece48c32bb6af85f53e73799ffb33be8078c +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..79c5a0a356098327dc61f7521f21f23987e05b29 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/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:eb4b6034d7edeee67b4cdb1c0e62ec3b63e4f1f6ec75fc122b6f39dd6d48b8b3 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e33008cd207bada998e1e541d3547645cc42bf3f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203ba77e934a82ea41d8c34e0f4d08b087fcaf43a268b8f714846daac7abdcb9 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..a2eb0494770fd26aaba13f63acbc7fab9fb95b0b --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8d35b4157ae456c98389373243cfa7e1cccc04d1677581626e8f8e1ce8fe3b5 +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..af79782089f719b9e7038524303ae54d4d32641f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d11ca73a620cd1e6a9c42995a282e21fe401161b6a38fcf37c695bff1dbed392 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..e93d946f6f963f05ad165a37e9569bd9beae468f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9affaa702f49730597456663b85c09fa62e0ce142b973c224e49dca70c96be +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..c8fbfc4646a56dc2da499ff3800c240b7619d7dd --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ecfee632eb4bec8d572568dd3111f80b13ef842072427e5db67cc60202e052 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..99d91d84ee7ce6fc15f8af630d20f12aec7f58eb --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a000cffeb82f679c5eea33f850666a8c70d17499ffc7879cf41417a213f90c +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/tokenizer.json b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9be9eb1b44c8e42a31e17665fb0bc09351598f92 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f06e73802e2c22916b6a34f2949c5cce9c95cff3a6c62a54657c5bdaa3c3e0 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa7136212442783ad5c99a841228aab0b893917d --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9b011e0a59084276402728678fde5380bbf43dfdd008172c0844f536574a32 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d58418a1c489040b14df6b66ceef968fe162708d --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/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:f596999e0ab4c1517d8b69be05b8e7ac028a4d7a814a3d213a25f1d89799ba10 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7012ac8e6137dd4bcbac3f0076551069911751e3 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/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:c037b66c0a0fdfd4a63069a8b384e0123abd0bf3b097c06a5655aadb0b3f8564 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e18e4789eb107b376c59f3923625074d7f8af477 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9afcde71478a823d1d58370b829905dab529511d53a904b12fe9cf3d7ce2bec4 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d84b54c1072a8e8ffa981b54eb4c48cc82faa07 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/global_step128/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a074ccd4de01eafe9dcfbbb8206815940d6fee0b48915cc47736ca2f8330c6 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..30f47e461994c09ad2552e5d213178a113bf9802 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c293b99852953edd26d5c4bdd31b1f5251b2dd92f93ba2d197db6440bd65b4e6 +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..171f55f7cdf7275feb023e7276515e028f30c47c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ed873fa216ad3004112eaa2a9af988889f71fd4a88e901626f817eaa3500f2 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..38a86ecd8cdf806a1ba6e8cc2a320f260db56c76 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1df544bb04c51e75c4fa7d1432b6a8da204bc6b52a1e9c14b6d390e4b2823bb +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..246beaa0ec82f69629c2bafcef7100df278778e7 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41fdfeaff44f58486e89ff7762e44ecee0964f91d35ee4f1fa11646aa0b29bd +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d08ae64295b57090bbaa5d6676253533d838873 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72d1751ecd37a23ecd20bd8b9260f394c2f370cb5db8d203bad7d01395f4fb8 +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/tokenizer.json b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ef1a2bc4b501c7d6288484b7cd31f179c347ff1 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c96a7cefe2851b73837270765d718127fb969aee9a19cc89eb289a29f43555 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..302ad30ea79ff149d390e9c0398e7b37fd43b5e0 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60cd44d80d403b7a18eab8f13cad1ef9cbb9c2ccf07e5d574be5a930b076b6b3 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..adb102e8c42428ada889c97855bc4a4e41448fcd --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b49b5fba4fef837652357c32b500e48eda036cfad15d116f4aaf8c85399c5e +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d60f97beef2a0cb57162b830eea98497f2bdb75a --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2a24b8318864af69723f5c5e61250b4f56c077ee9896e045dbd46689747d40 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8e52bf997eebe01b3d9a9bae5bd08ab00fa76c0 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c8140e4968d374c3a417c1b492ae124ceba9d4b9d971665f57f2bb006d197c9 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f87cd3fd63aff040093f9efb2109b624a7c2a4f0 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/global_step192/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff46a66acc6c3d06e44bfebed2e54ff1184be363e32191b7718ba9fbaf86b1c8 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..edb23cc8b145000cd524c5799b1e87d9251d12ac --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3972d3c5b97d2621d29242a995b4a2c3d89b5aea1f6e01f202d52a8d7da377 +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb10d002b8b42876ed2c6db8d16c890bc6581a32 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9adb3afa7b375218ea1ac31554bd74ea6b4b5b455077d1e46cca45a15b9f8b15 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..5e8187c25c9f848b969ad6c84aad1d51ccf368bb --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b9d1bc3aac44ee313dc6e0310aa07d6d2b090345d25a29da37ebdb763743a3 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e6cd3bd338e8574801b6ae73ff8d145aad1b3c9 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17302bb1ce6240049518c53c15ddb14dde9e004838572c4572e645e4a7d04819 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb4e8900ca74d271df161df3e78c5e3163d3ca2c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac63e93328a0491bc31c5b67747712626467b0c1fab68bd8f3a90d2ffc2d318 +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-192/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f002293590648dccfd3014c6bb7526dc2aba6e28 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde3c513cd0a68a62d7a17badb4a05d64e8997a1c239b71fe36d1315de56c74b +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1a594a9185be6ef2cfc87db594f4064b54737e4 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ecb6e803700d11a42ba5dd0329394734d99de73a8347d0b7ed25c0d44e2a870 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34c215eab8af0fafa9e77c8eb3c00cd1814d290e --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c3ebc23fd63b1f0a8d64e8eb85979cd33c75d20a1cd2473aa8807b2d9ecc4e5 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4974cc1b2c9a412069985619159571289ebc6fc2 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ade2f4dd20fe1e5b2ad397cff6a27e64432a68998848ce27e36a73822e93fdb +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f418818ad86f93c0e4612d9618ab80802f6efbe6 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f04f3ad101e9fc156025bfd111653e68df2a8b587d014d3196bb5eae56424c +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7906123ae13534785ad5390686a516ba2ef00577 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/global_step256/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad2bdfea5b411531551b68cb332ae75c5a1aedf0ff341532c7ef7cb9e1db7212 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..53198c76c46b7628bde1b26c4003929fb9389fff --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef4f1c717912b8c2a095986ed88aa24bcddb9bde45eb3754200896a0ba2e5b2 +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..b986b3ecfa72ad2abdda2709941aa778eb663fe8 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f282b0ae4246799858cabf25326e9a979517ce66a04d138bd333b8049443d59 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..b7ad646a626935dbd0e986f22e8bd7f643c290c3 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ac8d7230d750751cab455d7ae3a157e801c1e8872c64291a8bb9a3f395e061 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a4104d20a28249d206b64b9c0beedcfba7e4467 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b132427a761cabc7b3b61a0340c33dceffe3b9d4e3d7afe8c3a3194f9c9bb3 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5da175406e5951634027623c46687436be96a222 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8495f527d2ae384d255f961a1b604892e1f5459d17e99146a7b64167ecb9365 +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/tokenizer.json b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9716b3969b3dd9238bb420c23ef2b4f800f7e57 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332146dd3079198a10d726a9ffb3d39fc895db62e397a6928bb3803527a26741 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4885ba83825382b3efce389e90b22b999d0a2367 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe541b177ded496fafd97b75c7d2c12ac34162718c802bba7add7255be3ed09 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..162c3673ed90fea2e15d1abdba9b4474ec0c41cc --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d82574090a2e1120a2baeb701bf36f6b272a6211abe03c1a5cb4366e815c499 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d913e3674ee99a43322ba1ecd00bddb946fc82f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bbe6ea63f3175c4b03aedeb8af99e9b3745ec9b22cea870b0944328d878ddab +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ccd2e94c18f44e0c3cc95b2db9e89eed080e8bb --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d958b903d0adb1842c93fec768669f2cb559e4a0f88f8bdb7340031e178405 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9aebaa941e777b480fbf96b1e71ec45dc0b0cc4 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/global_step320/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d1deffb97cb433d3154e3db69daab5b34cb0602c67d371de2dccafc5782694 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..832857d1ee0fe8066e0898889cdff8c455d370b4 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23448105e82851618ba7db6dea49e827727dabc4c0d8460e9765b400bcc7e5ab +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..535a36afa5fdfc6ac3306f8120ba0ec273d17f3d --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbfdbdf1088a8112f23b8ef400975c59dae74a0519501a89981022536300ba57 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..313364f4bb0de2ee1f97c48869f263781a216685 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3a93cf2caf044c936d147be00a5a7d964bb6fbc12b31f102097921fc0a67d47 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..a99c78deab0dac5ba6bfaeae41620f1967bf285d --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49522cb521dadea2adcd931304cacb335ea6e99c952ab48dda7e341b2198e144 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b635ce1666c50e816d388484f117d6c351b92d3 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da013ae0b2b98d7666c2dc2fe7c1c09f26c72a818d58bd9b5b49a1d1f432bd5a +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/tokenizer.json b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e4a69c22941b06b3260cd1f8242f505f3fda3491 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa77e9ac35e681b14e4ee333cef3bb43df136ea7971fb1c232793d866f0f6a3 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..396b500421ff34d8596950d43614526633a5a959 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/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:bafa70ac9cf43281665247f99bbb299a4adba6aec961327c7c723221ce125744 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab205076527a4df98dbe1ee1dbd3ef181c6630b9 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8083aa746356a06c3ad6557cd66fe36517db41070d6fbc8d8e5847fe1556f91d +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..180538d6f55a221868f219b83d391f9118a2e9f8 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a464ca6ddd8df979840240f1dbf151fa56ee0103001b6647391be3432cea749 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0903f5d054e13a0e9f763044c518da62bdf4e234 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/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:da7c8a2751812068d1ad66e73489f3ba316282a6cec3c01f75f20ec0c66ea8ad +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad2a4d9d0fc1f7805cbe4b733c4541af82a3962c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/global_step384/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2002fa9c001685e1fe37b428805674a3defef93d4ca192bfb6511b6084501a74 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..a19d659ef33a8ca9d4137bf17866d34becf5672c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f52e08c009f92c3569485a797e5113bff8f20e18d39d1846280533b8eaba8fc +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..4685bc26cc4936376276d85f9c480873b4799243 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae502d7fd957e8cc2be44e29b658a95710b9da2f8b3ca4c8f7f1ef63679d0a0e +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e15a3dde67de1b6c4ee79abf78f437453b76a1d --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad3496b57095fc0b9d077a78cf4089ff206250f02b63e45310ae51d15d4f1ea9 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..743347a9c44cde60bfdc74ba33c9c6a30a2c3cb4 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd5b9ee83de58dcb3d273ac95ee2608566193e5b81be2643fe5c929eaa3d97d7 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e35447364346dd4e48ff2912c9630fa0d550dd81 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a73b3132edc693a316dd18b0560b36c0fb0501d1030453a31a1309122a6bf7c +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-384/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b6a4b8b6da85f78183553eb465da9a3409cd113 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb2b90197a91da5a72e5617b027c16db72ddebeae0fc0bfb19d6f6bcbcffcd14 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..23adbb3aff6b745c9356da550905a50b8602e908 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:659c43015429f4a80eb9d596a27cd369761480cdb75264c46fe2e352f95aafc5 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a71b1269d8aa5664f40d42a661c81e87d580fd23 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c4201295ae55bc087295de60f6006c19ab25933f288774042c6f40c4f6659d5 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9f8ddecbbd17f92a7cb3b0b3cef2d7c934679d0 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/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:cb16b1537260a2b5786d03a41549394f2ae6158231e1fbc025d1eeb5643cda6f +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..32b4b503f510abed31842af0da095be32e398ad9 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/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:a1b6c2bcf691b33fb264297193d8e87891806bb54613016079d0273eb0b8c0de +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..337d694607a09e882e40a3f760a192be22db0c31 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/global_step448/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac9e55f8574281f41f5b7c27af2f1bf8056298032e9d3e19ebb4032554b5b26b +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..fba1f698336bff1233eaa94107188ff86f9d5d4a --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c20e60fc1e39c6e2d03932774dc5cfed0f9d91e52990590bdd72a1f1cf71985c +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..251b24f221616a6259c60bee307c6f0b71e833f5 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b5dc971bce264e582379ea45f6a963a05ba077aa3aae87756de0a07acb4966 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..9caf9487c6838e2c74cfc97b4d2e9cd3659800be --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39621f14bd64eff212e66595d7573c91b4535d8c46be94f4d63e5d3a2482798d +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..51d2b7b2c37677371ac020ef8f513a3bcdd1ebaf --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04123a25798c359989c52c1273b985e06af7e63955a33233a43f8b23dee6d524 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a39d5aae7a5de28bbf7c8e26531da9f7f0cda3e --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d50e6c2130ded251cbd3fb239e3a2e1e0564766292c69bfb4aa6ba0d973844 +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-448/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/global_step512/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/global_step512/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a57e4a41a20de8ff03534a310fcfe36b24ae5c9b --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/global_step512/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bd261a2b1d54db92006627fc64b310c1cd0ac98bd321e9621a9f94a9c2bd846 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..62533c7738a3779d1e76faf38a25a4bbaf840a87 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13453c33295fbd408f926671f5873e59bbe38f898abb46bfdc6a6f7b90253a5c +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad985c7867de6500ef7de6ebd0b0512cbeab6231 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-512/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c320dbdcd1a602b0e1a9a83044b46596275f116d574f145a48322290b3257a97 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-576/tokenizer.json b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-576/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-576/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/global_step64/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/global_step64/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fdfa129e357bfda7e39b870ad70bf172aefd7e6 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/global_step64/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:be96ceb67c081bc232371d33457f1cfe6da7682793942333aa7bb85e43b9d0f1 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d6c93814d54cb5575ae484d24d7ae1b70c50023 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41fae893f6acd6a75b3d5c138e7276d2aee680e83997f2b509ce9bc79fc1bb20 +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/tokenizer.json b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..478194ab8cda73a4f17bb893ff0d098e240f3a9f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d2da55bb3b98a64927cdb4cb2136101e21dbbcde5e922d709ca8283adb72841 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..012c72c3d4ca105c29eae548f8eb56f5489cadf2 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae49ed8b4499861f72fb8daf914a65570693bd3975e30266d4ee3dd0bc23cd7 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad44b3f481314125fa34b220c71c36a56179db37 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/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:cb190ca67e113bf591f20d5a1b19df8866bf4b92bb376f61efead77c020f78e1 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ab24e85b410d53c5c8eeb8d61ca4b577c672451 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649c31b958b4aa0e1b7618484cf1e9941c3f4863703edbc17bda0c5857d287f3 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3357c8706b4ec6903dd5eb0c670f27c12064af84 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/global_step640/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c10ae6eb1e0838e8ac6e4adf9c84d20addee346615ee9c33c2c977ee0ac5ea7 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce72654f572f2506f27160b816a295cb0b390c16 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a218931437f4ccf43b090350bb40ee3df136a61635dc16c5ca38673a829c2bdb +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-640/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2b190551195bc95251000a02d0c8f6c1b19726b --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6e45f8c1c435dbdd47d283d0cfa60f3ee6cce3c19d328385dfde07431357b2 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da13a38424fc70fecec6a28e588b92d39b196e6b --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3af304b1d8d07d68a399d9f76b58f2e753b5dbacf6c6f7208b91b1b35ac5fd85 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dde4c9032623b3ec9be3ff50f22c38f967997684 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027e35fd40548067a964d51281f4b24ca7ab0d2c537462e4e19acf2b6dc75da7 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d2d1a49ce88b86f4db71aae454780a45af09ad3 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/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:b29f39fb0fff1797011c681e800d58ea8bfb432a2a626132869e5b02479bf5e8 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..526775f5dddee070cd783ffbe9cec4a397928d3d --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f84c1b1aea0307714d9a02a6d4f604d94e0bc02c435857dec7199183ec32609 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fe61d674c673c231ea144fa56641434667579cd --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/global_step704/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be169b0c78a9025406f3c4dfe82259179caa068f99250383d2a43ca331102841 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..788bcdff87433af814b303196876ac99ad41725f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542a01faca7eb7482d9805dcfa7432c82a80837df028664da1f30a060c58d73b +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..93df1bf4ef2c38ad171f94490164326b49659870 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b120c625948432e0c003cc67628a86cd0cb73f3e114bdf6f34b4f779b89eab0 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..22c516fab11a90aa4bb8d2c6413e642eca386e4f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ccd2905cafec7f0df59d995fbe4e600855ee2d6ac8043cd5422670b81dfa8b +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fed940bed83776fee227b5936c168e6282b54594 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11998cc5f35748b7722fb0b2c7a077a4a3e3b00ac72b4ef20efa3259e7892c63 +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-704/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c44f0fee5af128e6ea25dbcc1a6a44a18e6acfa --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965197e94684072d568028a85f005d87120104220dfcbec1913a27572acaa8fb +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..84f8394c5e102d534db8863ba3e11f61aaee46de --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04e3405239af8e48b21bfb5653c079c7b64828554ae76cf6bcaf6da2988cdc91 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..58e659261863e0dae01be158b349955efd0b3b79 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6071220441c46f5123ade3a023d4f479d1edc4fb5cfbf38786ba1bf222e9d14f +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85d17d8224917e38d1348fc577728a4d32665dd8 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/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:d7fa72a3f1106963d8e9a4fe6e355f2a9d4c02cbbbd300260112231e977227de +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb86436d7c97315c02e667c1b36bc2a8c7885d8f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056a469ffa70e973444b2b0a64cb8add7c6ec151d643da9c101de71e6ab603d8 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a708d0b68ed66704c5f4d2310fc0787a9c821b0f --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/global_step768/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc3869fc188926143b3fb3c00e095dc8c945ed2ef4fa35a1a85be6b37f496a9 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d1b0952653f914a94e908334f197a5a2581cab2 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa6788614d2b57e369187379877eabb793260b54cc557a73eb61ae4e10e3cb5f +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..f9c28a8a675af2b2394d73ecfd05bb86bd96e852 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74501678a93c364c9430dd58dcf0699ab3452bbf2b97173b887496d692518448 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..dbad1177fcde821cad43e57a45bb0a2660c9ce46 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48264a6b1c2105fae637e20e50b84f7e35355b79fdcfca53daa1b85533437a07 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..aeebcff1d347e8242ea460cc4e4103884d7b363b --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04573eb94622eb987a54f909f614f67a144034e36338da5f7df1ecc0d800ffa7 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba0371866ff4c56375788d8e6b6ac204eca2f3b8 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c26f336522cb69594b3952d10c9ee7899a17aa4a8eeeb9d1b384b971fa4c183 +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-768/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a511cad21a152d358ed1f6fed95c00525e30cbc6 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb56502c248ec083925d3abaf595b5f4ea14ec6f96bda04c7fa7d5c17605fbf +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec1ea3065edfa1e7c424f32e7fcc8e425b8850e5 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f11d2f9b924e0ce94063891bf2bef8a3a759a66efb346c7d5846c740252d3a5 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6829c40d66fe5c22a9e18f389b5acb44ac3f5dd9 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:598e8e36274d4ecb83e7ac08e4a25232f0d3d50c86f965a5a16ba44332e15615 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb3af18d8194e2fc92c270881b944c01b38fcb26 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/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:edae0642128baee2f633350841cb64de41ec7c50b78ff6a613dc9ea516ef88fa +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..40538c9ebe7e3f8956042c3132ffc17b197fe0bc --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/global_step832/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf06570b27bc1da1e352555df3a052b94c708542d8f7f445e6315df79164b801 +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..e623d0cad8126f9e1494a5b87fce27a511015570 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac6f058d1b7771dc784d688c20c56bdb26b005baf0d2ec0b8ee69125c1bf447 +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..0f440b79ac1550527635c706c9a8a2bc93ea0f35 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e729d020761a9194ba5c1f6c1f860273ac3cbf6eca424e120424db88a8414561 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..2f71c7b0073f449f111bdfa763f7e80858f47629 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff9cf7f3262178d7aca4d9d7d3b0d7d22d7e9efa479d7e73c0b4a985279a9770 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a24f5b759e8c4ece1ed7bb8066876276a80747e --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b146a7f29d6b9b3f36878a041fdccb0e237f35577617d80843e40e3e8bb3b978 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..8718467d126ce6bdbd53d0dbdd54da4de1ff11bf --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d2ef8130fc98df19a3863a629f0a8a22986faed3b54d90a56462143208d671 +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-832/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..67a7329bb28b14607f08ed250a501e87d0e99ea3 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59cac322676a4e0029d7123dcb27e3cc6c7b3bf5fbab2f41b2d78db22afa36b5 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..dde22b0da966b5d9d6717996885f151810953fa0 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/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:d461c04965b0aa0e87f04c71aa8904b84eef156fb8b4bb4c76e317ce4bbacfd2 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a2adfcdeef835363e3773040d6770516bec4d9d0 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/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:e12c76baee473d10ef42f3fe47752d2c6c4a3d07bc5e255b2ea87f0330083168 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d99a4407115909108d86a400dd33afe756fa2dde --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12cbd15851c1a1ddc021ff1b039d424017b9f6a2b151f913d72fae7978fb5bb0 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/mp_rank_00_model_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ef7339f8fe4100e8514c430be8961de3a2c10f8 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/global_step896/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6590cea7a76d9047ab9325eb440a0618524b3dd62ef31f2ee09a77bd4373fdcf +size 128985 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..f1d5929d4c63201ab61d9f919d33cdd189ef8553 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e99fa7d222cf13365ee7a6dc582f949f94356314b7ce4825664a282c29e5d87 +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..843d37e6248a47cc16446d0ba78f9e80e437740a --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11095b2928fc093d4727b52f321609132d86fcda1aac2b9df227852c9fd000d +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1c9a1ab93b6d0674d05a4dc7e089b6c8782deb0 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20840a2207a39b2ac6306aba976f31c89cadf40529db4e1d0cc6eaaeb6ffd59 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb31b428195e3d6bdc582885fa810f17ef38e377 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d5a873c5ad75e662535ecd1e781691eda6d17ed36ec66297d0c944b84e2dd2 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b4ecb0ccba616e482f4a3ec4b8e0a53368e6fbf --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfb7bfa2c34c711580edf233de0f324b5ef962a780aa91f27b4eb576e2588ab +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-896/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/adapter_model.safetensors b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf163e275681be9a8ffa5fee814dd1d3f0b0ecac --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f9ef9eeacaaf386f44b6c2ae2dab951513766df7c15d12cc994db2977ae224 +size 90096 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5116ec688c20f7b9ade56749b7a82389150960d --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f9bf00e6abe7af3713a9073d8973764242ba6f79c16ac0cdf9a7350a9d8110 +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9a3b4911538629d32df3e2a52171e8a573c3b52 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b7a037407711569392086191b40c633a7b77d67ce5a39f77861119a7a2dd25d +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e5d40b8b6a5b633be8c9b2c0db1ddad6bb31014 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/global_step960/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf82fcfc42be909afbc5098184854a78b74b0d9966b9c3641af4cc019d1b94f +size 134021 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_0.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..e84c5351aa637c22e6a22675ab3cae1a4ea14255 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bc39b280eed4474ed7a0a7cf7428d3614a512849c537f8153e82a96eab5ef5 +size 15365 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_1.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..100a2223d33a2cbfa925e7cf10542a2db632970d --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777b7d39195842aaefbf93910130ca2c9044cc04b3d7f06e6625a8d5ac78c377 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_2.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..620b07ff05ebfa136f53a19b17c5e40f165b124c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4667fa91fc1d061035b66556cb6d4f9aa60f6d7dce3952778adf886345a36800 +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_3.pth b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b890e02b705e5a74f20e07e76dea592e18d203b --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815c2021d25ddcebe13a02794ffdd0aabc5fdc1f87266c7c49b0d56907ec4a6e +size 15429 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/scheduler.pt b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9eb04204506c94bd661dad83fc4b7f80d132d458 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0745cbdd2c0a3caae7131e38e031d01350e2e6b8404ec309e908eeec7592a96 +size 1465 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-960/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/tokenizer.json b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/dapo_layernorm_qwen2_5_1_5b_20251127_195534/training_args.bin b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac17e830a9f541837500b71e4774e6dc6edc076 --- /dev/null +++ b/dapo_layernorm_qwen2_5_1_5b_20251127_195534/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed168d6a9589ce234f8617f4a5c08efc010cf913d062feb34c93bf908724b319 +size 8913 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_0.pth b/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..c114802788213446c4e71a6dceb0d12f52dbbf33 --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37695776b048a2fc9823b1db718d7b6b165ca714f2d73b6f40e44d8b24cd7ab9 +size 15365 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_1.pth b/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b07bdd3c0fa31cf321754616d2cc4971e7c2f86 --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d371667909b86be22dc2c582df3907ac70389d098b532bd4299e8703a6cd9aa5 +size 15429 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_2.pth b/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..dd199f6442847bb0e5a90935516affbe4c6c698b --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-1024/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acab289111d1ce3d9937fd53219d753fc80e9d3ed8ea6809d19e824b8e3a4945 +size 15429 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-1024/scheduler.pt b/dapo_lora_lr5_20251129_222821/checkpoint-1024/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2756a0402e887747498a38e6a02a416a9f22cebe --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-1024/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e74aec018068891d93c31fafa429298bb80bfaffaa27b9b15b00d99527a49f00 +size 1465 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-128/rng_state_0.pth b/dapo_lora_lr5_20251129_222821/checkpoint-128/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..53d56788b7096d055023a8434adc34e76888b38c --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-128/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0e5bf73a4587699247854f3f7a4f12ec4b9b552682af179924ab3345de4c30 +size 15365 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-128/scheduler.pt b/dapo_lora_lr5_20251129_222821/checkpoint-128/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5079da4bdcffb2c23d6c821c102c530a30f96351 --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-128/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80cccb159ccd60bc717839e315b752925e9691930463969c9644448226264bfe +size 1465 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-256/global_step256/mp_rank_00_model_states.pt b/dapo_lora_lr5_20251129_222821/checkpoint-256/global_step256/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebc629ca291ba49d1370e0d93559f3e30460b76b --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-256/global_step256/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:976bd91e9f991cafc81a6f8958155af627858dccfed238ebbcf66373d9ccdd4a +size 74161305 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-640/adapter_model.safetensors b/dapo_lora_lr5_20251129_222821/checkpoint-640/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f622bed30e14749caaa863d311eb0662ec1b7694 --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-640/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ade35599594eb3ba684102c5edf5462e5d6486577b14734dc2127a675d22a0a +size 73911504 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-704/global_step704/mp_rank_00_model_states.pt b/dapo_lora_lr5_20251129_222821/checkpoint-704/global_step704/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..166d28241ebfb804a871b1053696d98d8c35f06a --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-704/global_step704/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dfa4cf4edce5cdea3e741e4c27c75fccc90bd054c7b4374761c416ded3d92d5 +size 74161305 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-768/global_step768/mp_rank_00_model_states.pt b/dapo_lora_lr5_20251129_222821/checkpoint-768/global_step768/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6145ecd5d2e965b164ceb8b921e748a66c78b771 --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-768/global_step768/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5f8a337b43a9dec0691b35afa3ae6901ac775f7b8e1c19879db32e125396c0 +size 74161305 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-832/adapter_model.safetensors b/dapo_lora_lr5_20251129_222821/checkpoint-832/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a657d9800e89461a1178ac383174bace2ad06d0a --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-832/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fdf8c749462242db2f4b87ca06a1a94c9ba88e0d0a01eaf37a959aea6c78757 +size 73911504 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-832/global_step832/mp_rank_00_model_states.pt b/dapo_lora_lr5_20251129_222821/checkpoint-832/global_step832/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b08808174de5682032907fd8a653885a4081085 --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-832/global_step832/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67e4e40c20e9e8e428209a210708db760330356bcf222b9a51b72f4d9e53e86 +size 74161305 diff --git a/dapo_lora_lr5_20251129_222821/checkpoint-896/adapter_model.safetensors b/dapo_lora_lr5_20251129_222821/checkpoint-896/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..121db6c830a2246549169936c663ac4b8f13e41a --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/checkpoint-896/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1be89025b48238688eaecd26225a8f5f25fac047727d39e38cfc37d23db4614 +size 73911504 diff --git a/dapo_lora_lr5_20251129_222821/training_args.bin b/dapo_lora_lr5_20251129_222821/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..e78e81b63006cdc50b56c1b4072bf15526a95a70 --- /dev/null +++ b/dapo_lora_lr5_20251129_222821/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dbb2821af3bd665530e3b952a48404896a15b24fe94e9581441c54cb95b8adb +size 8849 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-1024/adapter_model.safetensors b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-1024/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..292ac25b477fa31f62c0b933b33cf190f89ac9f3 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-1024/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:626cf5160857aece7f740979a86c60a2be5bbd35a8b6e85beae75be80bef1889 +size 36981856 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec358c513942ee163b74d1e11a8b317844e19deb --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fefbc07ac2846fa558aa5c7189ebc0fb0b117d207c1b33d7ed115e821530881 +size 55408773 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-192/adapter_model.safetensors b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-192/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..112f372bf72bbdb3329720280a44b2277a6acb9b --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-192/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f5e2d40deffbaf3bd2014f75042789d82ae169ed2840eac2b703b71ae30a816 +size 36981856 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ecf108e64949e57cb34b9315ce29c39d15137c1 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-192/global_step192/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:f9f7921e652cdecafd086da9442f53b932f8104e2765c2bfd0f353a890d1e02a +size 55408773 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-512/scheduler.pt b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-512/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..4800a9e5803399b265ffcab0af9c3fe980dbd948 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-512/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0e61c4f166edd4bd232bd6fbefe6d67a5b7e00cb803d1741eac9a6d2b7b6ee +size 1465 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-512/training_args.bin b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-512/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2ef46f35127e9f6f00200bc2417ff10aaf2e7c8 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-512/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4934408abe1007a252a69d5ce6748ee48861a0e904d53901a1aa856adf4e14c6 +size 8849 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_1.pth b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..f8b8fcb6b3f368ea1adb3ce6cb93d48cde1f71ff --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f5f45118ff3c77e30be069846973f9bad0bff4d0120335e1b2c08dfacb69e62 +size 15429 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_2.pth b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..6bd05d7a6f5fd0784a2e8ac65d2eaaf7575dcbf0 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0fc6bb4b30e818c5a6e9e7c570bf00b0d2145284d8c7f98877832b53a56f580 +size 15429 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_3.pth b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..2026b6098614f03d79d298e0591eb16f49a2b664 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeab9f84adec9e22bb7912866a05ecb42d85f431eafe7457b0ad4450e5bfe154 +size 15429 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/scheduler.pt b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..454813a4990df191f6951cdef743cc653ff31f83 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:105f4404298e62d6811a76a80078eaf19c435d835ba8926a324f78dfdc9fb5f1 +size 1465 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/training_args.bin b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2ef46f35127e9f6f00200bc2417ff10aaf2e7c8 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-576/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4934408abe1007a252a69d5ce6748ee48861a0e904d53901a1aa856adf4e14c6 +size 8849 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_0.pth b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..27b3a6ed85da65f3c29fe8ee674e728bec2daeeb --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cd5dfaf07501078dbae5a00ed3a47c10e6612e966cc4e5ac0291d2adc082bc +size 15365 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_1.pth b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..892b2fad7825234a8f702b8e883e8236bbc22c67 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b987103b73281fc4aed7acb483bbebbf17a06fa0b482447693490ac4b587502 +size 15429 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_2.pth b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..413080815f9a8ac998b49b95e83de51f2848dc19 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c9bfffd0e693ac380ac4feb307200a1f58d46a2b3af86640f1d18a62e96c14 +size 15429 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_3.pth b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd0f393b59c4ff19287aee5fb0d8a9b5b569ff8b --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa39d9a52b8272fc7d0425142b0bb83199ce64b632067accc5c442eaf4c6af3 +size 15429 diff --git a/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/scheduler.pt b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f18e6fbca95d9546e2f67129f5c8f7ba7da9e16 --- /dev/null +++ b/dapo_lora_qwen2_5_3b_20251129_022228/checkpoint-64/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93cefd10607223128e502b13dda034a13939769cee1c2b5c47751dc1ef0425c6 +size 1465 diff --git a/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-1024/rng_state_1.pth b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-1024/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..8bb25f676b520cd36349deb435dcff933d8cfd30 --- /dev/null +++ b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-1024/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccb196d70a286c96384090e8da89c2eda4c677edebb9659adfdfeef3df02754d +size 15429 diff --git a/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-1024/training_args.bin b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-1024/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a32527c071ce3323255d067df17ab72b228551e --- /dev/null +++ b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-1024/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7cc479e21276b308c8f336b99be02d5fb11c440dea3134eaff10d6dfd8a99cb +size 8849 diff --git a/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-128/rng_state_2.pth b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-128/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..2d2060b83df571fff90ca57f2549f41101d24846 --- /dev/null +++ b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-128/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6192cca1e0033d1c18c0e877a9a4b350f1836f0966fdf3093032b23ac5d3631 +size 15429 diff --git a/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a1afddd86b47fb21cdb3f4e2e0d2a2adbbb7257 --- /dev/null +++ b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7954da99fdd4e61a049c0d62d04704f3a0a93d8a31ae9a4cbc2c8197b2233d2e +size 55408837 diff --git a/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ae13f35b7adb8931c470ed7dd250be295612c79 --- /dev/null +++ b/dapo_lora_r16_qwen2_5_3b_20251124_104900/checkpoint-384/global_step384/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f22274df2f3019b579757402a0d9597b7da28b924ab69e4a64a94e23c590e93 +size 55408773 diff --git a/dapo_lora_r16_qwen2_5_3b_20251124_104900/training_args.bin b/dapo_lora_r16_qwen2_5_3b_20251124_104900/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a32527c071ce3323255d067df17ab72b228551e --- /dev/null +++ b/dapo_lora_r16_qwen2_5_3b_20251124_104900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7cc479e21276b308c8f336b99be02d5fb11c440dea3134eaff10d6dfd8a99cb +size 8849 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-1024/scheduler.pt b/dapo_lora_r8_20251129_135342/checkpoint-1024/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..99d91d84ee7ce6fc15f8af630d20f12aec7f58eb --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-1024/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a000cffeb82f679c5eea33f850666a8c70d17499ffc7879cf41417a213f90c +size 1465 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-128/rng_state_1.pth b/dapo_lora_r8_20251129_135342/checkpoint-128/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c13a24f73f423dd71ec92a310771199ea5f8a57 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-128/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04fcc0a3cb80a897dfbc53bd63c3fc427279ebc6add680b826e8ff249bf4f3c8 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-128/rng_state_3.pth b/dapo_lora_r8_20251129_135342/checkpoint-128/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..d9c6dafb19ea63e819f21b4d9172aa7b2ec009ab --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-128/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cb8e6c1b68058503dbad57d2ef927868d579d85c82d833fd72feed95ddbcdd +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-128/training_args.bin b/dapo_lora_r8_20251129_135342/checkpoint-128/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..489d1fc6a9879879650b9a0275141e44deaac832 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-128/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e591d12c15a6576f59af6858dbccfa77b59d60b21ef7a813c92a6711b9106af5 +size 8849 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_0.pth b/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae34bfd71f9e8097c3a55e122d601176c9093144 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc821a38650a86c9105356d7bff8cf4b91e6f891152b7a91bca3e6348f26f994 +size 15365 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_1.pth b/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..e6aeb6834be91e2d0047022d66573ab75bdb3594 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe1d3cad7d12ffcb454094e1ad0be74e6815817f4d28828a255156f7ab33abf +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_2.pth b/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..005dc7cc9ac0f5ff207347f8f464e9e34fc41a37 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0d5dff0b7ade9c00eb2dd4f9b5b546f371b574f85112008ff272026f18367b +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_3.pth b/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..816faa53061c4067c1a1c0edfba2d58c82449bab --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-192/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd2fe7f747a1d7a35baadecbc55cd712ff654e645f1abfbda49e169cca418b56 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-192/scheduler.pt b/dapo_lora_r8_20251129_135342/checkpoint-192/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb4e8900ca74d271df161df3e78c5e3163d3ca2c --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-192/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac63e93328a0491bc31c5b67747712626467b0c1fab68bd8f3a90d2ffc2d318 +size 1465 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-192/training_args.bin b/dapo_lora_r8_20251129_135342/checkpoint-192/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..489d1fc6a9879879650b9a0275141e44deaac832 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-192/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e591d12c15a6576f59af6858dbccfa77b59d60b21ef7a813c92a6711b9106af5 +size 8849 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_0.pth b/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a3d235c3670027c899bbae05daf2e54f25cbd58 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27348312795587ebed15eaac809e8b2bea7728a7237804461c27d8bd8f4f06b +size 15365 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_1.pth b/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..214efa1d107bab33ee1682281675a51615d308d7 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e05c1baac2d43b2651ad66084d14275fa4411f43a965315f873cb5bd7fa093 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_2.pth b/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d6e0490bd8cce5841e1dcce74ffeb6b7b7c53b5 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b06e771a3418d39cc20e51c46862d1603cb59e09d3b294b339a325beea5e876 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_3.pth b/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..96494feafdffa74778c410104ceb1e3ffba96317 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-256/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4fff8e38c7c729bef5f2aa17742989bb5010914ed2b93e33f087b93348d045 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-256/scheduler.pt b/dapo_lora_r8_20251129_135342/checkpoint-256/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5da175406e5951634027623c46687436be96a222 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-256/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8495f527d2ae384d255f961a1b604892e1f5459d17e99146a7b64167ecb9365 +size 1465 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-256/training_args.bin b/dapo_lora_r8_20251129_135342/checkpoint-256/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..489d1fc6a9879879650b9a0275141e44deaac832 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-256/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e591d12c15a6576f59af6858dbccfa77b59d60b21ef7a813c92a6711b9106af5 +size 8849 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_0.pth b/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..5daea552efa58ce34a7d8e11e122e6acb0a75268 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1bab0c864602e30f6e11cf77e89bf64e59b3d4a4fe4d30c13b347358e3c2a0 +size 15365 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_1.pth b/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbf57ee3ab4370312c4e6d909a2b5773fb066c12 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f00cbb38634adb586d07c5bfbd311d72aec2476fd0b3170e37b520f7d542f5d +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_2.pth b/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..04f09b79ea4e4bbacc4db4b53cfcc55e1e1daa0e --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bce1d74899f6a2a53f15cee0c4cb82d522a51cde8ad0950db6368395ca345d1 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_3.pth b/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d965d0a5af0b71013e1a87ac89dfc981e9fcda0 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-320/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2687a04e8b1c2ec8707f2e3916f300d4935e0df0f215bebc1213d8897a3ce491 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-320/scheduler.pt b/dapo_lora_r8_20251129_135342/checkpoint-320/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b635ce1666c50e816d388484f117d6c351b92d3 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-320/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da013ae0b2b98d7666c2dc2fe7c1c09f26c72a818d58bd9b5b49a1d1f432bd5a +size 1465 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-320/training_args.bin b/dapo_lora_r8_20251129_135342/checkpoint-320/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..489d1fc6a9879879650b9a0275141e44deaac832 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-320/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e591d12c15a6576f59af6858dbccfa77b59d60b21ef7a813c92a6711b9106af5 +size 8849 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_0.pth b/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf7a03a834ffe82befc5f5efe56cf5c2e2a2487b --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06af586bf8622dd576669e87eee6a2f3a6447a9df284ea8096fed1d3aee5037e +size 15365 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_1.pth b/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..dff32046500e03deffee0eb256299c524a2b9279 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839a084c0ecae6966ed310912aa0c1092d9c79b5d18c991a02731739691af5e1 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_2.pth b/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1a82ac5d8fcf1f66e75eccbbec0dbc00131ffcd --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7dc0e7a2d11b69ff05cc572e7c5abf73ed6bcfffd3cdd5989865dd1a3033382 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_3.pth b/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..f4063eea15f22f5339357583371cd26e8811cb63 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-384/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd71c7711122d0f638221f8cf7e9b4e0705ef1d67a95f0c9cc689de1632e88d3 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-384/scheduler.pt b/dapo_lora_r8_20251129_135342/checkpoint-384/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e35447364346dd4e48ff2912c9630fa0d550dd81 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-384/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a73b3132edc693a316dd18b0560b36c0fb0501d1030453a31a1309122a6bf7c +size 1465 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-384/training_args.bin b/dapo_lora_r8_20251129_135342/checkpoint-384/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..489d1fc6a9879879650b9a0275141e44deaac832 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-384/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e591d12c15a6576f59af6858dbccfa77b59d60b21ef7a813c92a6711b9106af5 +size 8849 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_0.pth b/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..804b39ac2b814c36e8b710b5ebff737992ea5d0a --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd6c62acead0c274df45df3860abde5d075dc9a107b322dbb77081548b2d5a85 +size 15365 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_1.pth b/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..f59ed479ff2b5c3245954200dc6b59ba1313ed9b --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c6e4cd048c4911e6048d763f9b0da750f4cd9b7713c68f83e772b05aa6f15a9 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_2.pth b/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..432903617f31228e42a0c9d1660dca99d74700d8 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0ea82040ba421eabecd4baca4104ea9a06e4a4ba7d7012219ca00e577e5b3d +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_3.pth b/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc75b2e943aa5f9762e197836841f22c4e34b559 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-448/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd0248b5efa943fe036da698a5e52f0bda128c0a18163d82bbc209e72309a790 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-448/scheduler.pt b/dapo_lora_r8_20251129_135342/checkpoint-448/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a39d5aae7a5de28bbf7c8e26531da9f7f0cda3e --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-448/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d50e6c2130ded251cbd3fb239e3a2e1e0564766292c69bfb4aa6ba0d973844 +size 1465 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-448/training_args.bin b/dapo_lora_r8_20251129_135342/checkpoint-448/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..489d1fc6a9879879650b9a0275141e44deaac832 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-448/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e591d12c15a6576f59af6858dbccfa77b59d60b21ef7a813c92a6711b9106af5 +size 8849 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_0.pth b/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..3769a2c72bc6061e53d8c199af43614fe0543cfb --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ff8cd73a158fdec569231d7235289664d806cf1335a61d15e1767f765a173f +size 15365 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_1.pth b/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..bf0326950c0be0dc438537b6fbdc31e25269a1ba --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a968d960527e9e28cf404410497d4aa4b30513eb0a02cc6d7204fb2122351c02 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_2.pth b/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..743911a001e3e5576110e4d50f73bdd695e1969e --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-512/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c87dc2acc4275cf3f3dc137a859245530f1549a2b28850511fd3c0c2f3f558 +size 15429 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-512/scheduler.pt b/dapo_lora_r8_20251129_135342/checkpoint-512/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..4800a9e5803399b265ffcab0af9c3fe980dbd948 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-512/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0e61c4f166edd4bd232bd6fbefe6d67a5b7e00cb803d1741eac9a6d2b7b6ee +size 1465 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-512/training_args.bin b/dapo_lora_r8_20251129_135342/checkpoint-512/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..489d1fc6a9879879650b9a0275141e44deaac832 --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-512/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e591d12c15a6576f59af6858dbccfa77b59d60b21ef7a813c92a6711b9106af5 +size 8849 diff --git a/dapo_lora_r8_20251129_135342/checkpoint-576/rng_state_2.pth b/dapo_lora_r8_20251129_135342/checkpoint-576/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..90370507a1ebcff7aebfc8691f9601177717530c --- /dev/null +++ b/dapo_lora_r8_20251129_135342/checkpoint-576/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c5aaadf281b1c9f2914eacc68cd496c2693a42e43fdfb501aeb8fb82e746515 +size 15429 diff --git a/dapo_miss_openmath_20251129_124147/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt b/dapo_miss_openmath_20251129_124147/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..14cd9bcd9f151ba2b86483dc320f3ad35ccbfd0b --- /dev/null +++ b/dapo_miss_openmath_20251129_124147/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477afc63137eef11f9fe9de11be2c95f2d76cce6175cf9e388eec2c0beb5a069 +size 503979621 diff --git a/dapo_miss_openmath_20251129_124147/checkpoint-128/global_step128/mp_rank_00_model_states.pt b/dapo_miss_openmath_20251129_124147/checkpoint-128/global_step128/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4235155975ceb5ddc36013caef928f52828988da --- /dev/null +++ b/dapo_miss_openmath_20251129_124147/checkpoint-128/global_step128/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a012bc2cd2cbee36153752fa6b0ee0284ed8b2005e1cc8ec68f6a8dc2fb0ebd +size 503979621 diff --git a/dapo_miss_openmath_20251129_124147/checkpoint-320/global_step320/mp_rank_00_model_states.pt b/dapo_miss_openmath_20251129_124147/checkpoint-320/global_step320/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16773d540a20f284814a9bca8407f36a050cc404 --- /dev/null +++ b/dapo_miss_openmath_20251129_124147/checkpoint-320/global_step320/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2fc74c110c571bc9b6cc6a81124366cea77919d510926ffd24ce9604ca8b056 +size 503979621 diff --git a/dapo_miss_openmath_20251129_124147/checkpoint-448/global_step448/mp_rank_00_model_states.pt b/dapo_miss_openmath_20251129_124147/checkpoint-448/global_step448/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ffbb903ec5b3051c60f88d83e7d4634d08d84b7 --- /dev/null +++ b/dapo_miss_openmath_20251129_124147/checkpoint-448/global_step448/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35b4460cf18a7406853fe840dfc76f17860c829549ecf58d4023208f0ef90700 +size 503979621 diff --git a/dapo_miss_openmath_20251129_124147/checkpoint-576/global_step576/mp_rank_00_model_states.pt b/dapo_miss_openmath_20251129_124147/checkpoint-576/global_step576/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8c6134f8ce8c3a992dddac08e8841b57454f301 --- /dev/null +++ b/dapo_miss_openmath_20251129_124147/checkpoint-576/global_step576/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac163ef9b7dba8043a8eb44485c069523a67df55a944d2e77558808a4bb9219c +size 503979621 diff --git a/dapo_miss_openmath_20251129_124147/checkpoint-64/global_step64/mp_rank_00_model_states.pt b/dapo_miss_openmath_20251129_124147/checkpoint-64/global_step64/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..08c331160ce03e56ba310034e271da9ca8d6d66f --- /dev/null +++ b/dapo_miss_openmath_20251129_124147/checkpoint-64/global_step64/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5bce52bff4c9e7a956335c88d8d8820248b5d061c6be853e2ffb72e06e562e2 +size 503979621 diff --git a/dapo_miss_openmath_20251129_124147/checkpoint-704/global_step704/mp_rank_00_model_states.pt b/dapo_miss_openmath_20251129_124147/checkpoint-704/global_step704/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..51d7c47d5b1a0954f1ef7f29786ff0f566b2da3e --- /dev/null +++ b/dapo_miss_openmath_20251129_124147/checkpoint-704/global_step704/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133029bfeac160199da739f10bfaa47e3ada24f6072c7b83d9d25eb8c3ffe6ff +size 503979621 diff --git a/dapo_miss_openmath_20251129_124147/checkpoint-768/global_step768/mp_rank_00_model_states.pt b/dapo_miss_openmath_20251129_124147/checkpoint-768/global_step768/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..25575eaecffb377b5fdc46231f16256ae74890b6 --- /dev/null +++ b/dapo_miss_openmath_20251129_124147/checkpoint-768/global_step768/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2455227e1b003f5e7181aaa3c52dbceedf4fc9c129b29076fca4613bfaec53fb +size 503979621 diff --git a/dr_grpo_lora_20251129_132413/checkpoint-960/global_step960/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/dr_grpo_lora_20251129_132413/checkpoint-960/global_step960/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8f05a8fe89b29e895a55724d573cbc4c01e6bfe --- /dev/null +++ b/dr_grpo_lora_20251129_132413/checkpoint-960/global_step960/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:bfbbce29c2a24f2b4054a4acfaa1d1fb46a4c751b2cf85e4ff0bb534b1428634 +size 55408837 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-704/tokenizer.json b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-704/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-704/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-832/rng_state_2.pth b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-832/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..7c014279abddb45b542475945ad62654b8be8168 --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-832/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd7fb62560a9cee9a7e0e99d4e776c80538735515a1798045ef22cea9dd7451c +size 15429 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/rng_state_1.pth b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b57b81ba4786219a6d3f88e98b3501ddf89392e --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a16fad06e9ee965a56adb8f0dd3b469e6ea47932ede485f3021d9ac8b38c5a2 +size 15429 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/scheduler.pt b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..63a66598ab1f1095efc57532e4585d8de8b03d61 --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99384ad9258383a500385935f983aa263b846dfd6cb7d670505c3b498c231c8d +size 1465 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/training_args.bin b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..aecb99b3f26384aee356780c931fbfecb9e94e92 --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-896/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe5b31134a094422fde08c9d7fd4c7b9deb533ab123345f5a4814519decf5bb +size 8849 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_0.pth b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..01fb817679d7a9116c72f459602538625bc018de --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f8caae146ed32068c653c1b56224c455ec5ed57ce6405c1be8e48951fd7bb6 +size 15365 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_1.pth b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..b225f1f651d21e8c4ddc245086110c7b1d047e49 --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c597f391553d54f12be2db6d8880e47645e2dffb141e421f5cd5d93221b97b9d +size 15429 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_2.pth b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..087c8eca2dd9f7ccf5abb21976b71b39815214d1 --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c71a800f0540171668c64a3b6107a6f990fcb5ec87877a05d707cb95d73c879 +size 15429 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/scheduler.pt b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5194e80f873b8bf25fe87de3bbe7c0317b9d5d7d --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0f2a22326879e1ae044cb8551fdd41f4878456962a8646b19ce19e1650da4c +size 1465 diff --git a/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/training_args.bin b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..aecb99b3f26384aee356780c931fbfecb9e94e92 --- /dev/null +++ b/grpo_full_qwen2_5_3b_20251121_111716/checkpoint-960/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbe5b31134a094422fde08c9d7fd4c7b9deb533ab123345f5a4814519decf5bb +size 8849