diff --git a/.gitattributes b/.gitattributes index f5429f6aa4ccbefb9f905d1f2ffa3f96e75093c1..f75e880c3f1f351b7eab0201da0db516ce725c95 100644 --- a/.gitattributes +++ b/.gitattributes @@ -55,3 +55,6 @@ pilecc_cont2-r1-ppo-llama3.2-3b-it-em-warmup-0.05-rouge-rougeL-temperature-1.0/a mathhard2-grpo-qwen3-1.7b-4k-step-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..071be248af23817f836e424f3107d92d80211f2c --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8f5a411aa84528c462cdc9bf780af3ec80c0d75d02b0ebfff14708be96dd60 +size 14632 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..a184c1a63e12044271fa69c66785a004583920da --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b899618a6dd15c98582a3f43803ff5263150c3a53d760ff1737cf56c3d4f349 +size 14632 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..4310b905739c8c19416af43937e80d0d37f08828 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc6e5c51ca52405eb41f433f5860a57ee0e494ff2f63cc931e1139b45c5fd73 +size 14696 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..22b4fad682cd8a0cb8b8337b4dbcfd7d2747fa02 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbb8a4521e0df155cb957ddb4fc856f50aa8667b0b00c77ac5e9245f0f4276d +size 14696 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..027aa6e1700506bdc34329ad7688e2d049abdc4f --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb9f004dac7d65378dead9e59e1324a6e0f86e1b59b2092eba2429a2a4560957 +size 14696 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ce725e4d314d2230cc7ca30620b1d11feba17b5 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1200d4db318d80aad29adeb8c23d6e4b70841947e4f992f319dd74c09a5755e6 +size 14632 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab8fd8dd75d28dc2abb22b35edea75432f5c6483 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9bcbbcfd1e9ebf27018d7c089da7289ccc98a5a179d954d281b8e5373daed71 +size 14696 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..44caba39f41aeb009f05f13f9e530399c273d192 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/extra_state_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b5213d4a025f32f16434f08c66132fda8a4968b3cd81240cce644de39f4786 +size 14632 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e211517cf6708440ffd4664be8728ed6dd26a88 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:118ee7a55b2a3830e006ab60ce653768b6b567509359e28a5ea0be44199d3b7f +size 4998767360 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f940f6a8dbc63393c4e8801375d0c22341179a60 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e55a57dc8ff391091a7077c793d94af9aa55ac96df23cbd658fc3209ed3cfe9 +size 4932808968 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00003-of-00003.safetensors b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d492a4dda494b237b5b1ecec9a3b9814c764bb6 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c07dfd34aa0ce2b32acdcf8d7913d8f43e07c10c3f95863fdfdb12338c2aaeb1 +size 4495462048 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..34ec887f2ccfde8afaec399a90fb34c5289befd0 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d511c388d7dc5a2acf15d21f3c4d76a0040706d4dc2862c571e7fec6f8a23d +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..98b2afd29b4172e13cc59b8498223c05eab4c5a9 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:916590835c04ed2b3ec7ada1ed2860d0912d542038f344bb10450fdca5e86f90 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..307a2463adf29d7a96d9e9a5db1f04434076a293 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:653055c9bdf6a62c11add323dc0a3adee3cc16f1434e5981b99dacf2e375ea43 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..866e90d81e45be10b26181a56b0340befd97ba1f --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9bf4d8678d0af984761368af50fd694f9b2e5f0de0c2c058bf24c857fa083f +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..3cc02cddb9eb3a2a59b7d99e045643890d094dfd --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66d3ec5dceda230afd25c5a9412b454a9e4faa67fd8ac7b6445f3ecef23a92b6 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d81c00c8bf5ccfb7ae04eb1174241e75601f012 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e938ac17dd0cf9e294cd42e5e2531088f8630e4f59e6fe0fc6b7db4f5bcbeb +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4e9b19dd1a5f1a488da32c0b6053285ee33efe5 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77857569c076fb5833efb064a6db4fcb3757f30421433ab78eb791264665ac5c +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..3cad0752142c1e3fc17861fa1c7b1e06bb45971b --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806d12365be15b4fe16802c8c1c2df0904b0baeafe4be61cbb456bb74ef7b8e3 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/data.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc6a52b8a8a2bc4e9cb18df254125f26f3c69ae0 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b242e0cab009584e039e858f3bf59994ae92005796749b56637c2ae169fcbc +size 1492 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad36b7ad355bab3d5c88807c73a14a6f5d24dcca --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4ff68a4636e4f82e39b1c89fb9b949d72e2f0d457553c0a7032b8bad6b6d5b +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..4032d4f1fa09e70bea4ca0bd5c5f4659536b70ad --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ab908272cc540d166cc9a0a85934e95eca9706861716830900bb3f841a5b38 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf5221f62971c9d6d00daf5cf6646b023784e3ba --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98cc3e1bf35a40bbde5dec700b3c579dce5d3f21513e5e8208fd9c9bc8fb50c0 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..19760b51d2ccdb3d578921e50d6c4df068c34a3b --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5a0915d15cc09669207efaf319517ca754160bcc182366955b49cecfed55a3 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb1155aec293b6478158521a39ecbbea051f395a --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d625dfdbdb8f3ce770badd80c04cf765bca257c423b00b20c1ebacbf1ed728f8 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..b53522fd83e51a73fcaff4ccd3f323b4c4ec52cf --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:859406df4d8e3644116625e1887170e15bfba5f922e4f75c2fcb6489a565ee75 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb72650dc1cb2a58350c25fc9bdc54c653a631b3 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207f5f08ab63e9f997c0df7e4ec9c0eec84cddaf466b2913628138b040dcd65b +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9ca2df85b8f362ef4e11a62541063368c9d93a4 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8376a2d87e1d46630a2eff109e611c75bcbd302dca9c8e057a6ce27caa0743 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..2daa66f56fe2dc26b93fbcbf0e20b23b99ef7393 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5626ce21e9974c596009e5ab8a51fc7beeec797464541fb40a444b2f745ddf5e +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..99c7581dbc814bd1f8bcf3d77ea9e46ba7d9a7e5 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86dca4cd95e18caf39d94cd25babb403dc6bed032218d8e8ff5867a16d6fe48d +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..94e982cd103c2f2af4b54087eb69488a55c1aa6e --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3a02b0dd74e2c7bbfa831be2bd20d8367f3ecc443d20bda96312b2a0b606ce +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f9ff33a6d3550ba69117c5904453b59fe19bf19 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5f1c8186cc08260cf96f1468c3997c41e299c6675c6c373bcdd98e2f67f4e68 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6973a544a343278d9e045fc6c0c47b111fb8726 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9600758654403d87c4498f8fef0afe721e09454120b9d488ba8f0c31f21f62 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4314d42c3bd59d976834be2215e664ea4bf3ece --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683f83dcbe2cc068c756aebc695a251f9b2671a41d73b5cd37887c020a4209da +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f02b832218a85d0d998b782085e793777780f65 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef8a16893015639b999f27d08f605d0c1d3c0c08c115c7b3bd90615dde860600 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..e664f70f6105497eeb761b44cd5163f58ef6e84c --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f4be49a40ae908f39530e25ba3325a4bfa3a8bee5a0b06a6f64ab654ee91526 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..4215f052c0b3e1f346ab43743bad75ce1f9bc049 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbbea0137010e3b26e8b5c1d30e275f8e6c364b3697adaf3bca2f8c822e3a0c0 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d204438b16cb06667318e88bd6930946b774275 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c0d300dbaec48394b709b895bf4bd318b0f10a56248536ed63dfcdd95f322d +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/data.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..3bedfc33515512ebb039ab318b2cc5b02647c22e --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c25d7d77721c6320caad8e4f0c25df3062a6ab7f8d897c6ce1449346fbdb93 +size 1492 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d9164da37f6aeaf80becabf80780580a6f11cd3 --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed8fb1e600d034a08fb1ae21b80934417c4acdeef1ee903a24ae20c909ccfefc +size 14696 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00001-of-00003.safetensors b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bd21e7c61595a10441fbda061ba1a2607a8f044 --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da2bb4041178a72945c9ae703901ad3e7b621bc3ccf39ea187bc2df092bf5b0 +size 4769980416 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5a72b0a5ed5dca5aecfc2402631558784ae2ab5 --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fa51df74c7d5d0245826e47194536f487b0a002510bcd387802b77b98a00fe +size 1803528186 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..4dbd6d31931c0326d5abcc48d6e2c1c44dc5f487 --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5596f63296f4c6fbe3767609f53d9d33e761a9ea717734e99738bdceac22d910 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00001-of-00003.safetensors b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d5287f277e16ab45592c7ad0e7466adbeacda9ac --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b1893e0b0906a4ba5f4073467256dae53285b75c4160801dc27075d8afefe27 +size 4998767360 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00002-of-00003.safetensors b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1d4b9bbd585fd7071c4522d608618d16fa800c1 --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4ce210a5f58ba403c5095d27689439e6a7f3eb23e61df9f7feeff5c1b2e34e +size 4932808968 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00003-of-00003.safetensors b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab169d34b6c76ef59c09db37f9ed14255c44ff9b --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2614b0804ff4ec7ce9dcfa457d6fc3f24b78b2cbca025fb18fc36b6e6a959aff +size 4495462048 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/tokenizer.json b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/data.pt b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c3008d666c90e847d05cccbc858d6b87b8f7655 --- /dev/null +++ b/mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a75ede5c91b8d96773b0f9c06edb86fd169799c4eaee492b81fc2c145479ba49 +size 1492