diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..7e4cafc9c04da1bea58b7ec5e6edf5148c67399c 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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-0.2/global_step_100/actor/extra_state_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc1090d95b30e3b7fcf61b0894653ec869e86f45 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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 sha256:8e744400c0252cdb3370040dc464e647f2599be990eff438cfa01b4327620cde +size 14632 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.0-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..ecbab854238d9432df5909b1670a761301e2ab16 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-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 sha256:8b28ae9b97ec52d76f8449cbab090d1337b244d8d2dd833408ea80defb374c19 +size 14632 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b1d1e63b4c10cc9f136a2cad61ace53bf0fd2ea --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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:f3f297c372d90f495e24fbe7a7d823b1503187ca12c628dfcdf2fbc46c48deec +size 14632 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f02a9c3988b348e045957955a405fb0e02256a7 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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:ad3e8a4a5bb8ce55834c3ffd41468c075f1782ea91494d9797fc4c31c3374655 +size 14632 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d3142bf4cdbd238ee90ee2afbad8346d33d21a5 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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:ce6d08b4a4a5bd962516d201002b76bdd70deab3721bc451230cfbfa3cde1e87 +size 14696 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef0cf45d4a70a3309d1ed83206b9645fabc10c71 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/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 sha256:16e674fbaf15f351c3d95a154dbeaabb583ff6720217eebd4f4c02420a7000f5 +size 14696 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00001-of-00003.safetensors b/mathmedium2-mutualposclip0.0-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..1c95fd9da9cd4a42a92edc145a525320eaa63c7a --- /dev/null +++ b/mathmedium2-mutualposclip0.0-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 sha256:70f07abe77b6d8f117313e3d761c4bacda0acd8224a027865602344a2d273a95 +size 4998767360 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00002-of-00003.safetensors b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd40485a7acd9dda166d917d9f7e6c177ddb4e67 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b5778f6b16e64efb35837a32d9736131cb2812d37b6190304e711a7ea115fc8 +size 4932808968 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00003-of-00003.safetensors b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3bcd77f8040c25f2513a3ae2f39bdecb4fa0ef9d --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c88b90eca61ecae82c99b6ca0eaf7e96861ac9b1d5f9b7ee0367e26b03a31c8 +size 4495462048 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json b/mathmedium2-mutualposclip0.0-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-mutualposclip0.0-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-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.0-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..1a46455317f798d3dec5b0ac28203fad6e313bab --- /dev/null +++ b/mathmedium2-mutualposclip0.0-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 sha256:1aa295a5f9e41fce94720ff196b414839e5d38a39c2dcf75237c9a38b69449a5 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3371decc6b10685760f3183e076252dbb4d8c8f --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0fb3954532dc7c4c408ca80ebd5d0caa84077f2797053eb9a1a5596f87e71c +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..1856be5c59d240a564ff1c42b5e8404902bd7882 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:578ea3ac948cd40d7cf5531691061c88e1f8bdce9dd754e99190d8b31beac012 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e44f35ec159e6e208e2f0d98d0ff670038ae1c3 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6519144d435de11d47f4ffa51df5cf899ea856f88b97cdc3b8ef068f9c0b224a +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..632f4b28f8a3eb112a6234a9cfe0df377366f934 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fa0f86a71a2db5862a45645ee8b6d212fc215a69cc11354744f3c32373c895 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/model_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.0-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..63a60ac22d3190c859a831d2adc64e4aefd2e103 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-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 sha256:028013ae91d5bb7a7d29a36ac2cf351fe27be7b46aadff22598013111442505a +size 1803528186 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..69336bdf0739b83c6d377374e11eef92db2d949f --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54b0cc3cc5407609761915dfde428946fa56c710c82b371e1b5083e444c081d9 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5eb11bc1a00c4f309d73a6984c1354689a543e8 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68dad06721d792c6a1d15f0ccfefbf28f41c9b46a756856ed801968ee919c4fb +size 3212775159 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..418ebba1bdc86d7f1c1ff7849a5beaa50863d5e7 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ebaa3a8ae9e70a6bd1b165982c3ed1bd83295f9af81f1abbf1f44103472888 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5a86a5b6faa32a26efd46df69ba74118bbd5fd5 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c557db4e85cfee73c93b25557ce6073a44bd36637fa56a7c0bc9a677915d925 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..c18393b35dcff66a1833c8af4a7a26099acfd372 --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23339675406757e969d0d25d900f0c5843c71f68cd0e3ce387b239a205d0bd2b +size 3212775159 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..924140e34340dfd87af652d2d7dce72654cd992f --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2e98c91b1da8560f7f995eb88389c224b0c2083ae97830c2c900149745d990 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4e8d676cf6465fa2e30affec127fb4004d5b84a --- /dev/null +++ b/mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/optim_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9b3178c3a968bb9c38e529486fb37db9d938363b173394b94b68bcb9bec961 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..79167b3330c589630be52ce35b810488b5cb3bdc --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:fa5df99c993a41fc29faf83fe5e651f89b047ff4a706160b5ae7bebbbe0ee512 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c05f623e99717663860ee17f7d9c40ba9852b1b --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:ae8ac1d793ca3dc7006bf71cae3d71f9096dbab71d53c78cb2fa4d4910047bc3 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..2278874ff54bce215f1f5023e391afa67a682a64 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:041060543ac858c5f9fcae80babd922141ac5fac04ba0779a27019a0d983f7d0 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..85a4a4fee583dfaa3ecf5524ebb8b69e97ae6d53 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:44a7e98b05a04787014d8ca82d1ab6ad2734f20989b00c4143eef13e687a7756 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fb1bb7812cab823960246a156185069aa3700c1 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:43396fe5cc5cebbba3eefd28e1ee822d0b71dc3b223c4614cc770d80915c8c30 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e84b1eb8173bf13df5ea107a5eb8483ee35d37d --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:a8dc70239c774490c5ad9c5249e00f2be0bd096dc9e57690bb8a5ad996079323 +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..86d58913f82b88ec277fc4bea5550269291c0fc7 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:baccc26c4a6a1cc287a6cb91109ad344561280fa898f0c2fd74da8384dcb4f6d +size 14696 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..e873e45dfe0d848920e728aa76899e45cd7c472d --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:497563aedff3f9a6c72395c49a4fae9149bf69c388081c12cf4570c8434289e0 +size 14632 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/huggingface/model-00001-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/huggingface/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..70336df7545d75dd83d3b688f818565bfebe326c --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:fc53d6266b7d494d53b0bd462c6403ed657fe03d9655c830481ddcd06a03f153 +size 4998767360 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/huggingface/model-00002-of-00003.safetensors b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/huggingface/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3f65171d75c6b808773dfa0a44ba6204998273a --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/huggingface/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e462f5e24fea2c69aaf26115530a24a87bbe46d1d9497b9721d81980f8ba366e +size 4195762176 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/huggingface/tokenizer.json b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/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-0.2/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-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..29e04eb2384232f47fb3c803cdae839704067920 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:1362956ce46e2a2d31bccbcb7751b01cdad5e15cf56e7a1ebc3e876026b1ec17 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f5d05db5102f477d26ac398785ddd0c9d61da62 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613647725ec7110001dcd8f16619e035bf3d262b96a29a5ebbec4896500c12cf +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..a44f7996ff773b66a84bf33f37ad7a61f55373b9 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5d5e0a599b70822fa2afd8199dd4ce2b7e0a0061b2bca75d89f381a4ac7cfb +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c6d60e9aed1cc4984a506a9c7f791ea9903c1be --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3f4fe8a0fba5999bb6e655a3a9e37d04a8235bfcededf1d04b62495211ad86 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..db3fe4afa1638f53d64d51f36e8fd2c4210d6210 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:feb43d0558f81ecf47b013aaf51d5671f727d3a303cf546d85964225c69c025f +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..e582b76c58ee587ba1eb1809d495c55cc6215c4c --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a73bf47ee651e7806d77eab2b4ae6640965ca68642ae34703fb48b8ae0e8151 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..40c4d86bfd3a45f60b63fdc4810066a56ce6837b --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ed9f112959d55853318ea8268adee303452fa3444c3fdb3c32424081302887 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..28dc15b6b1befd19702648e58f616cc41383e0ad --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:724f380be1f3c7000a21d017362e635b9869ebf019aa34a16e67823e0b59d8d7 +size 1803528186 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_0.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..d10ff8a19833957e7ed8d1e1957b062497f02487 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9fd9f1cc14cc40598462e9c8abcd6114c898610c3c05a77465d46f50174370c +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_1.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..22d1eced829b4052015eb8187e47e11cb141a6a2 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b6ff4f02c62d47de4712cbd9e0aaa66165c2b4f8b9250acff6d820674b8ce55 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_2.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..f32153c838d5f85af6a08e029980147c88be944a --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9565a0de85dad9b7fea4edfc8a7f1bda0b03fa2d3bf9fa8a64ffbc7b1febbce +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_3.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b7984427f2aa3b6dc0078c576e2beb7bd4d022a --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbab057af86a37383074009ea3ee664ac0b37f7516a797b8327a428461e474ee +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_4.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f99d70a501a1fc9a814550911bad806eeab0fcb --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a27174db26fc87d391097a88b5f8adee4e389dd82febd52d907a339f9baa0b09 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_5.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..abfb7facdb44f7945eebeb7e1c81197ec73143db --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b4f2c360f9e8cbfc1f25cdca1094e738432010bd9a1a38fc98669ef5bd5c0e8 +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_6.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7a1a69a08ff159a52312a4e6930b004cace0afe --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b73b99b4e547d407e7a7b8a0a763c04931ba29515332cab74bad1c0ccc9167f +size 3212775159 diff --git a/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_7.pt b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..38fc13e46a4618ffa0e4ff6c4e72fca4018acf19 --- /dev/null +++ b/mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_100/actor/optim_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:211fde249c2e043ab88ad2de6a2afbc4b3bb8a3e2df7b298f92faa32327b0626 +size 3212775159