diff --git a/.gitattributes b/.gitattributes index f75e880c3f1f351b7eab0201da0db516ce725c95..726dc2bf3201d869992c2b2fed0cf7d1628bf9f6 100644 --- a/.gitattributes +++ b/.gitattributes @@ -58,3 +58,5 @@ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step 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 +mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/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_100/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..94166de93b05c8df865a18aa875a6880bb6ddb8b --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:d5378f9d1318713d6ff5e1b27fdabef97ec2866075ebde45c0708e9bf22f9258 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/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_100/actor/extra_state_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..8724880f63fae3b0dad2db9e693c74938a893b27 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:9b3e34aba21a60161a0023a6face27c217ab654af373c11f0f3a3a875c04cc47 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..874263f4afb796c3d18af998b2f9e0674e483c4e --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:df4ac53f06c84b6549714e9aba8f1049136965c8f1abae685b5beae1785fed33 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/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_100/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..627a20910ab147884d47ac90ddfe441deaac6d7c --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:f8a8ad62eed68b8c8aac953981108334620a882e78f8b551dd354d2a5b1b87e8 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/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_100/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..935cf4ae2af05068693351e307869af7e3eccc67 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:28c3a6907e8422067af25e6a381fafe4438323af7a42236e666ba00892551f3f +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..ddbc2bae592d884b96ddd30bb4f68ab05fd50277 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:54299ecc2d7f0d0f04755879441cbd2b0e1077c856409c69df04a062ef53585c +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/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_100/actor/extra_state_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..4efbefba2751653eeb08ed6b40886d83789e43d8 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:6cb155dde2735638859c1c3edec47d85d1a69898be2dbdea5e80e9644434c2b1 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/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_100/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..41a4c7bc32f74a9f7dee04ac1c24a996d2d3c1b1 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:ee682c14324ced329eff7f7a8f86ccb64fb8b9c6df1f1b3aff55c710819abcce +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a3ad95aa4c0ce0a994270cbdf1a75ca9308dfa0 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:6dc85b2545b6e995b6bbf25ba57b80330f8607fc1e8beb7fd4f96de11b7b5be7 +size 4998767360 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..497fcee5e455ae7c2bbcd5c9eaef8a46e4751ff7 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:968afeeaa9e0954f49566dae1848f2185e34e296b881577c6245b0c60f46e94f +size 4932808968 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..18b61e45914c626f0e3886bb1fcd87ce329ba98e --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:573b163c34e52b7f7c5ca8da71980b4ae5c219bcf65338e4f4c0996a3d578ddf +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..7013d1154006df903297e7202fc82bb4b551b9f6 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:cb47755a2efe9dd12cbb20ca273ae8705085a576ab559a7028c0ff0b179720da +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..d15a7800b18731e92d75c04c4524340cac14f236 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:35616258c34969da15201af13896774feaee27660100c1fe3b0966326cf0f6a9 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..b5a7b3c44f727e0a7fa6e071cf01d431f6ed91a5 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:a01ca7826afd9137b7cbc2bb94e0db0637ce2eb5ba74c5f2013c9a53036c8f35 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..615ebf0566ed377ca787b8f5380f53d3e8825120 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:55393d72be9bf6c2c51a8c5a82727438bbf599611a1edf098ed4f837239b8755 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca3c7dc56a6676e36d02ecb7454498b7a55b9194 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:70f60a2b0c999d95592d6627176b2f3bd072f5f969b042786d16512242d859da +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0a50c6d739945584629ce90f7e247402cfdfc7b --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:657e084dc4028ef70571d5d9c6c5929f23996872e90da1b4f3a7ed23bd614462 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..64ed6e3c48a21cea057d35f20692e36ead9253f0 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:8b53847166cf4b9a8d6c6cb69c00b5d194a06d45e1266ee1d43359fbf6dacc07 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/data.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ac0f50438fdf7bb0cf82f341a115e7a089f301d --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70942094b5268cf0012483adc1c8f3240f18e59ab27f28f282cd079aa097e8a +size 1492 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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_250/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..a369ca673682e924dda973563e9b2c64cca8df93 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa1a0c801d1f6266c59a1398d561a1974abd45eca893f34b4114961659c1d3d +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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_250/actor/extra_state_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..50beafec833728281c320ccbc84c138fab6a9d20 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9268168cb5eb4d49fe2a36858c23559ab105696ab1337e13f176af396fd6de18 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..4388df1babdae898ad12407686b863e17ebae783 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f5757a2a940c9dbada2b08cc23bd81d354e9b77dc8c65fb300f716f18878fb +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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_250/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ebe3f4509a55b32fb27eba74eddfd9d023a42fc --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85c0714d9e8af0301dc19de33eb16daa7de4586a5a422162c5e669fa9b24b050 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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_250/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..288a2328977e6fbd4b92f04589f12aa72a6342c8 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ded6dca4c903b6d5ca53e3e3812a18ed7b134f61b16e308f8a5e9f1f85ba8e3 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..2518659326730eb41bc67c9cb4aa840fb86548e4 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:829f331fd554564792cf50927da503707386a33a3dd30b319333cfc240c9fd97 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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_250/actor/extra_state_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..496b3a1e767cc18d93f874c140c79eccbb29db16 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f804eaba51f71a0ee7daf278e75160162a499becbb16199cdee7f02ae476b66a +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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_250/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..161be6bf4b5fd579b44d0b482266f3a554eada06 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203559c991d67dfd541b63d1b59460b0081ce229b2318038c07ae1fb579ace9e +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00001-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b400dfeaebce4040acbb856c24068c1d515ce126 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c267fc34d44f10cdf03b82e50a48b301fe81d38457b49c8c4f7bd18adde74907 +size 4998767360 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00002-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..296ee7befd3fc79aee8a319b21b884ee28e664dc --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1eff99135d7c50f5c9e7aea46b827484496bff6908e95c8d791c026e54ea634 +size 4932808968 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00003-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77358788768c1164f1f11516338749e8a09dce9f --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c45aabe332a834869b7317805de045b0e6cd3442529cebb6bff7748a7fbec4 +size 4495462048 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/tokenizer.json b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..8beceabfab3e58487d8cff8b6dcdc6eced73400a --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e566f0301d51de2e1fcaab31934c0cc1b132143ff5695c2c9b7594de40bda7fb +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..0da469fa58378a9f4b6ab27890c4748c37f65ed1 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e563ba122253ca1b3fbc3a9399e65beea80db6779432e27ae6a7c7286b1317 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..49852aa0d90b579403bd54c3ad4d08598e963fd6 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454acf28b6a0b1b1112dcf6fdc1262c4face52a2b090a63f7bf2bc378de30ba4 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..e515b9f7e2a9bd62f235fe0b632f64eb1289b744 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cfe13499563ece2e96edaa1230c59dbe6159459dbca1b447648a335291fbfbb +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7b8713f55b957cf7d2e5dcebc77804077153aae --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8cdb709097f3aba4f8f91c2bc9788dbfe20b0c613d0f594e14b3f688a524ea +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..185ec9fb5044609ab57ee4ae02dfe1d9519f2af8 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c285f5b84db3e13e4e54e211594b43b714a825f690954e6c8d880c90025f4a +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..9eba32625b197242338f898d59cd472f812d6148 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ea97645925f72cc0cdcb90a4b32e240e0e39a8ea354f02b4b056aec631ef59 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ee421269e24bcc4277fc47c2011ec75e43abf92 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd50a321157e8bec4e8367999b4871119e9589f87f2b79a14b047efef2d7007 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/data.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6f0cfb767fe6f5fa2224a82761f476bda4f6538 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f7b5ea5c3e11506d33811ca95001f5f2e24ab491cd6697d5054e96a90cf4cb +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_2.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_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..23ae6edfecaa9e62ef7cc547b7bf7d733e4feed8 --- /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_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf20e63362aa747876f85149101ecbbcb05a58a763c999ecacb1c2001e2d7661 +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_5.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_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa82f76e0eb5f1b8eb0cc06f15ce71b4e1d80946 --- /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_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816e2078b526fb5b5ed1f35eeb97d729b8ca41670adcca568e80ed1861c943ba +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00001-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..754fe390f6ac6db1c836261a7af2793958ddd7a8 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcfa35df7eedb9d0e4d7dee8d726ceac7db4b65fc719ad0f3992b951632193b7 +size 4998767360 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00002-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..60851226bbbe460abed1322833783208106bbfcf --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad3d3ec0d7e48d5f07c5ddcdd3b7709bddd553a9318c07022084b5eaa498d439 +size 4932808968 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00003-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed0e0e0003282d6f2159b5120e573ed27bb69a16 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959cf6521363497e9a2bf49114ebee92e83342d8d9197ca67a7e36f9c0ce248e +size 4495462048 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/tokenizer.json b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/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-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..965f341793fb8d1b84e00ed90b0a8002821a15df --- /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_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fc93bd26aa971f0096465a935ed2cfa5e0cb5e62a39ea438e2171843ce77af +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_7.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c86d2c30de2b347c1a86be4522dc05f6d459505 --- /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_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d64c42d3e332f54167f0944c593d10508f6fae0ccab4a6bffc7c4134afc36911 +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_0.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e50399fc879a8af2e6002c87fcc776e013afb9c --- /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_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f81d527372dce7097f6f19060bff57c2040bc32deb5c518c615681a808c14b15 +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_7.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9638bf4015fa63703476fe01351faecb6a6f22f --- /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_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d31f1ff92528bad1ff4de4d4b8b9bf045d09a65cec344bbc53d6f555608cfbca +size 3212775159