diff --git a/.gitattributes b/.gitattributes index 460a464fc223e9c80a379009cc72a3d2ed348f9c..6afdc69b24d8a9997fa403d53ffc6adf059a81bd 100644 --- a/.gitattributes +++ b/.gitattributes @@ -44,3 +44,15 @@ MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1400/actor/tokenizer.js MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1700/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1300/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text +MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..b92f67ca006562f2faa02a2c13606892077fc814 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/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:f4bf49c3c4cbc9e64fd975d1d339786e8c3db26bb8f3b279b2ca7e7c4af672d5 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..37ed54f6de818f9ae60287a3faf3713e7495335b --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/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:ed03c7650142808ff07bc44b437e3b475106100dcba4ddcc537f19a2bf0315a3 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6e063d152847902fd2d4a8b6f53e0d98a82f1bb --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/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:ca1882f96c2568802079183aa05c1952058977f11c138b522360bdf5d3ed9280 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ccc76789237e4e61d2fd6f76831d06f8d7fcee3 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/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:fb1f17a93ba931ef0b29b29a2bedde287d31921625a6cce86757fe7e140e32cf +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0d7d0df8362da3bc22d49660a3468a9a89c9b0d --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/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:a7af677573108991f89773d274d06f4ea3a3340711197619373a9a4d1e290e60 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..16a08788410d364110afc96da08a81e1d3f83c71 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c982e4b22d9638d07b316a3e47700bb214e87e37f4fd2198f351346ad45e2c +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..6fa47ff8accb9aa187957440b7d631a4cc549e5b --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/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:cb47adec38d001813c4f43fd886eb4397216e94faa98b517e1b51789078ec13c +size 1016091450 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef221dce9e374e9229e03511040c5eed7e1c94be --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8155e0caabfec8e9b1d7f04dc16d855cea40f012ac0b4410766e2112a1eb5391 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_100/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e15fcbcc1219406562ebaa8e3a01cf1ba6c16d3 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19489a629e94de218c951676fce66f70ac8e3cf411c42fb11167534ce9999730 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc8d101e555555f7a1999eb966d6d46c2609fb7e --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8bd729dd7deee4786fbadfe6bb90046b50554e804b9c2077d34d29bb2c72559 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd8b14eaa9a9e4fa8879885ec770ae1eb42bcef2 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0fd25edb6b0a2a46b693cb04fa542ce735b9ef742789bc9e6f797792d738fd +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..553aa0786d5f0c515f6c5b0a07ffeb89db10946f --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85d9f917584f571210f1d1f194c21a2a4877d9028e14ab72d7162e66708c648 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a7369420790a15e85685aa9227b27a55dc3002b --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6bc8c7f2238e13ad40ef785194b5970b6c7de14a37df19eea72779dffed81ac +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..6265fb55993f2e2a678c6390981e06a3b96fe7a3 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822a8bee2cfdab5e7c4b97604a7086e923090199853ddf64c6312e51ca6dcd90 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd0019fc951a31db9a8c66a05f41e84e933d3ba3 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51daa06f234171151e988c90ef40d41d802780ab03fbb06822697bb5ab03f2b3 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b35d71ee38ec9dbb17d4934b55e2a2e457ab29b --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c9bc75c8fdf0a334ee9934c1d1bce2d52eea0b44fb48da277fd5748efdc275 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1000/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..1351c3de1059b142867832768bea82f03df53acd --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45440a9e2f98533a80fa50214d4ed52c41d9dde95033c2b27f4a3a004b433bd2 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..005cd78b9d944b28f3b6dd8f326fa5d4a9959533 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715d3581c6d36b23204ede458bfa8175f943a1320fa193f5aef4e400b25dcc4b +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..182fe461099bfe56cbe052ff2a1450ddc962700d --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7755af12ff0f60e8a0650cf7d0916b4da77110d63e5125cb73c2df733455d0 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..5054076c23e5e98ea2514ea10e47c263770ced9a --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a8719eb15e80bd92a30a601c0138c6414f0126d29bdf2c069082928c3354dc6 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..045da45a500ea0bd6610e58e3a5f23e3784a14c2 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721f26505d9ed0f4ddba09c03c35bd75324da2a68541ed0b5bb54a19c57ce866 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab3c8e039e554f55168cfc68fd73c558e0963da1 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79a09563b8031ded16485713aa839ee1aad610bcb9259683960de927ab82f9d +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..db134ec97f40754481e5306a103fc1346a1db282 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02b38702e8ec5edcabe5e65c03153de3e493ca61cf137f294daaf4d75192a751 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..37b4d4cd7ee9ebd41064b485034b4fe3750488e2 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8629d4303ec28441ec8ce45130a86c2256b34fd21787c5ce5b1990c3b7f9bc6 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1100/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..aba7f2dc6e8960599ed1416a319f28c5b77d060a --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e69ebdc99885d6591fab4592c03caec9c3e74f9d086c48ce1cf01cadcad73b93 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..a68b5f7cb80e7e686396cea6d7cce5fac758b85d --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ff17c81c9168ca58c58222aa4f9e22a488c51df6a45c7f80de8ea5d317f2a5 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..a10b7c0390903248b6a746068960eb11249c7400 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ca54d738bf0edfa29114788e57bbea125a754e955b244b9ead224c47f98e1f +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..8359709380aaef15eab2f95656ef88804cfffeac --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebdd4f3e1103ec13f1bc825d5bee46a6ef6643338672a4de93e95d730ac8dd73 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..e41c0258d7d537e1428bf673a7a41dbb527b8039 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a96e97b86e066a1fc025c0420334015cc3c34d535c3611c1a33dc68f1ab24a2 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..15d93471493c713a81c6b885f5462623be8bdb0c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d9dbe86b11627878a5d51bda02136f32d1134f130ab3d4e25ab11d86113c9c +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7772a18dff56be811a57e4dd8f0be9b68fbc001 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1200/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4043444cde3668617dfd7fc10e76321476bbcfa27e03146fc3a5ee93722c6ba +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..4dbafea48fed61756fa6c96f1fbdfb0d27786b96 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e7a84195997de6d42c0e1b5dd3688400d5fc1f2a27f93aaf53e79c76412240 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..75dd4097f78e1deecbc62a4481476ed57dc4a30e --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573ff87f49d4b341796ae333cb921b7d8d233aed988c85bc3fb2f03f67d8a082 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ef2b47e7ed8166fb6762950a4d9f10114fff8e0 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57600d2fad157b6a7abc2a9444af8f16014824559cd1db278dac7b0b8fbbe7f0 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0fca9e01e2c30fb29c818c4d270abe52760d5fb --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:972708dbaba3e4445ee34d3c626eb0352605a6cbc2eb9773f245c26395d16ae9 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e069bde7c4ebbea1eb0f7bf02b4e0ae3f82a5d6 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1420426a40f8c119f0e86e1cdb90bcd57ceb4bebe96b0381df804cb1939160 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..9caa6a3407d4f134bf12a4277f6013936722c5b3 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:664256863929bb9afe112b2fd3179ba07a1b2e259f85701d4b5724f6d7d62eb6 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b6ef93f1e88b99df93e7002dd20d01b5a6a1706 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2d82cd28bb80fba14ec6e2542cc2cbc12ccb3cfee06257e6673939d661bae3 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..49f6bd0571e0af5c5e9365cda66a27ade362dda0 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe3ac62d56f78d3022c07032e0913922b281649136ec5bfef00f686146c7a7d +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1600/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1800/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1800/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..a59bc66b6e619da26d3321acb34aa0cd668a0c7d --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1800/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:336314cae8589d24f67aff720a7ceb1fee221b6a135d1a5fccbca671ad76b6ee +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1800/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1800/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c8aea6b70b28621c1f563817534cced0f136084 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1800/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7acba7c1f20108bc7ff564c4f169117bd7aa26178c5118d4e97d5e7a1da53a4 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/checkpoint/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/checkpoint/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/checkpoint/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..38ccb63d47c5ea338ee6280643479fb51795903b --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961e81352198b985e2f815d3cd8c0aaded1e78ee16b3aa5dbbae8b873d7b56cb +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..a782a83513471cc8f5b504dc10f0905746a919d9 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ea5058102873438034654100ba11dd1a3515769ce7da217c48f5309fb06ac3 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..a12261ddb24b7563760de291b8d352c3d9d6419a --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccce6eebf950abbe2068290dd0f575bc74152e7bde71ad702ba3e2c327b430a +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a3f7d135dfe6c16932300c69ff161898781604a --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1269bb511ba35395180b3235e4dd5a2c8eda75c921fb2a299712ac02c2a81b12 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1d317f5bc911615bcc5eb8165468e0a3c9e7408 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9dcf892a4e737a660b2a3ee308513bc83b9d2c5fbc7db6f7dc542ec41825c7d +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..bfd0e6c053f61ca28335babd583a6d08b506784c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba6cad7353b6feadd0d7aae6253340c5b98a01a90df34b2ebe3221b2d18f121b +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1b0ded18b602a3a85d76da5445dc2be54c4682b --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d1b28911ca4494c832646074f8ed6d815fee6cd241d9f6e70966fe839804928 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d94aee68d0bd190a368066964ac003b9c2e7e4c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1907294efbd685ec36ac878647cf60e1c8a5be7eb5cd6eef14dc3cad01c83f79 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_1900/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..aed4020a7117eada3b1c1828539187dfdc1ad9f9 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556019539b99fa9218cb4335bad217ccfef66d3e3f6665c9baa0f9c1c4c8571c +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..455a5159a63a2c0cc6adae59486d42cde56dd52a --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ceeae8621993eebc0e0d1217ac777e7916e7c6bf4969b6416fc485cf89ddaf +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..894e56eae5cfb7b35f51eea09ac98cfb264b4384 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1581b1513ae46593b6b2c725f9d3aa669d375343fcef01112497ba1bc11c57d6 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..92db0db1177941c7a776939800c73b55595d20d4 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a212785a7a4f167bb0c7f3c5a5bc5492d03214b5c708607a25afe57058cddc3d +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..df602f2c09a6d180d06afcb271a58abdb4f38ae5 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cdb66c7a5639c02797bea51743d0d3d5cf37d5d5a68c8f66806aff452448d31 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..aca90f16e96c86a92424b89c7050777adeaaeda9 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd3bba0f87ae6304ec0ee210ec7cb7835e73e858bd0ecb804a10589997d4781 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ef1b166d3dbd9d98418ceed20928f5d221d8817 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cde2f4d8c733fb1539bcba53377c44d59d4e6cc467bfc5320a86a03c7009bd +size 1016091450 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..266c59ec821b3ef268751d97d4795411f86be1bc --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d16be95a18c1ddbcb7097fe9a9d77005dcd0f55dc448fb0a606c6d44c549b8 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_200/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..411a6fd2013690d38e9b04be5eac5b42688362b7 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165835d04546e9f82c01db039cb9f2a3e59e2c0bc54b7f890d525127acd7edc4 +size 14632 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e62fe10c4ef6c4750b5c86b437a79add6bad481 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e8443a65fbc17c569e9e05e5737fef765f94f32e4ca0c054d03ce426f1c7e1 +size 14632 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..145fe6b071b77e48ac40f98014268af7030c9915 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78632f8784b30f8dfab69b18efa1f9b70ac3bd42eeb714c80fb5d4ce5749031 +size 14632 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f5983c3c7c6765c6e0a14a277634bb8fc8ffe02 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d73f8d96453a7553a57e81579e7659919fd591b0ac269dafcc773c62b39c83 +size 14632 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ecc2ad637a263b0fb0cf08dceae5c92ab73d70e --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64b8f61a8cf18b721c496c538a35a19e349a766dbb7b73dc6bebd4129d3b9b07 +size 14632 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..17477ece315cc1a4df64a3e39878d7a0b4126b19 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c787b8f92c858dd5d1ccde71faec96e8a3bc8e8c463294464a0681304f77da +size 14632 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..5011fe8394207fd241f8dd2a5d10e7c1b3b3a6ee --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fe24a9c2101fe2e56b720ee0e4c7d5c3503c32f3a0fb7e7f2a31a695233405 +size 14632 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e70c4f28ea66872ed98aa838c9b5af3489118e8 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/extra_state_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60bf8f3835a23b6e541b7eb17114a4f10ab6e96d4d10e547b967f90603551fe5 +size 14632 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..8054028edd2d87aebae5f0db8cfd6d09c85d1aa0 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17bb920bb81cfd70a1d15ec906b40afc20f5b81a0d39d72afed481ea55cd09a4 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..972735acb0f58b605429733fd3ab8d63a9c41e56 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7159a5485ba4239c7ed5ff5febe6a373fb4130f2dcf612902ddff4c2ffd00223 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c961fe25530593f3ffe4528ad03a02bd1024d9d --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f14d3a7c525b1791dd607ba44c9aa36bb52bbe9a5a2f7cc558c5fc47abf8c17a +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..0814b6e7281b619771394a935114a510dde0b08b --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:377555fee09c89e5dd0faa398be36ff79b5d04eb58d979db21d6fb1554f82b25 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..eea0dbb89ae5585cd1cd899ed940e484144ea033 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119e9a1e9614cb41913718608d8737329f95d00eca33036256a0b1d2265fdb75 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..ed4df67ef19b05f1b204363eb4ce7aa63eb02f63 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5f60b521eb0cad2f0726f7c1f1ae3a725621921daf5fa44650cc3f1a71e670 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..e49b27494cdb8de55a385d1773854fcfbba54730 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0f2b5d162f0706aee23fd39bef019799cbfdd17537cb5f1f4f8f38a539fa49 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ffc16deba045869a10d956ef9b2b67e7ecf0333 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371c002a7debc7ccbf66adbe6ce80793eea81e693ee7da1a5010f397a9f76a29 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bd4906e4219b6cb2a4bc4afd3898bea5eca1dd0 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad3303cfe2420e76b4bd35a5107b852a93b87b457cc1cff79b7ef3ceb3b37ab +size 1720601143 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..944813b7380ec959427921085c328a3b9278b4b2 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b901b72a40f010d2505bcfce7f7aa6a948ab38420b73ba352090c1c2285b07 +size 1720601143 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..3383590047f296a46cc52c583ad6c937b246137a --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e876089cc26360cb11cc80aa5d28cb027f5d1ce88d8ca8ac354bb51277652d4c +size 1720601143 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c9507d6eb3f22ba84cf17c5626acd3edb8c1a47 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91156ea4a6b3542f527a40cd06d76a2895a4f0b4b091b545602b863cd7f19a6f +size 1720601143 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..39cafb06515b1282a540bfc4af0d31ecb76a4c29 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abefa9fb19ed32471a90c3f7d0ff87a0fb4458baf9db59b57c2e5c1a1a0b656 +size 1720601143 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..39a794728faf23aae78cfee3bd86f025c669033c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:799c95f2751f101dc417128c6cdfb52e8a4a7b060ccce9d226a8b38999a14b7d +size 1720601143 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e79fbe7013d25c1d5908acf18ab29cb0faad97a --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8ffd1f95c81583c6b7d37aec71a4c71253ca017698edcdceb5173b3136fce0 +size 1720601143 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..63cba0c7313d02142b3dc40d06702472f067d32b --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/optim_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011e7f96fe0e446d6ff4b469e3e6cc77639f06098019e8318e723fa1b3761416 +size 1720601143 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_2000/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..435b6ff504d69895c32ef8d83cb816fc970e1791 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e1a0eb6c8f88c6db9d490033438dbbb99d356d5a4a279eb8ff888e8ef2ae88 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a8ca4dd097f0b47cdc43e0ebeabd9bac3e91451 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e816daaf60b330a9ef2a16c361cdd5eac17d327a9fbe23068ca516d75a36e5f3 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..29f365994dade9f30ada07901447058542feb79a --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ad0fe7c7baa1c7f4cc2eff9a76e9beaca2a0addbc5a15ad6197ffaff60f9852 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..60642f8a10e238080f0b7049ef6543168d069fee --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e993f8f5214b62b9c0a06b4964ec83a6cdcdf2e6917c8b902a9ae98636f9e9bf +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..6325fa02ede10281867b20a5630d9e04fdfb89e6 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1671260f3d99a4f0dc069852cfc0fddac7810b683c61d3e4bbc0388417f838ef +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..ced274431b972319922c623cd9caa54bcf0402f6 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:883181c658a6408af63d7937a7cc459de7d98a927cad27968788930d5e1ae09c +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..c88692bd9bf280eab76b07c7b71e1d76e249da98 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655cffdfad39c3f99eb9ccbd1060b5fefa1df5891b1b5d87c382a4424c2ae625 +size 1016091450 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..847937d9acdd3d112672d19e3bd88273e9324cfd --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b795fcc8b5844b3c8882f984ed2be369892fd51a22eca0f5d8ce73c772db676 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_400/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..df88b823487e074b77e28b42c5f4ca915f7ab7c4 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8faff6060449907284457b639059d00585c81da011638230103b67101ce489c5 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..f671c1d63eee55b201b082116c0728479aa7c0c0 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0cd06737b3a925ff0ee436493a8a70d4d602e203b9d2ae7c2ac5afa3e305157 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..c931bc813c278de3cca5b343569998fb2304f217 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54759ede468b35aa3e2315e7b004d4cd9936d1a487e0de90defb1eae391897b +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..dab676e5bf3c50f68982883d15a540a29c0d97db --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81b917d1fa15fec0e48aa9fe2c46277ce354ceacb38929b0c50b1faf1c17f1da +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..7dd129e3de036dc2f5c5d72aabe210b09ec07177 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e0eb9e7e590a49f9105fe728d63cb520d9a7c05f1c4697310c9948876dd6f9 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d1811027ce8ff4161417b95c1e1871a6d65aa79 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:910c96c9b6739eefb2872374d18f09c50b0f03dd157f502a5da0fd6e65173ba0 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..03891528ab2f03369bc21151aa38e8d5907fdc81 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d2d01f767a6c42646bfcf9242d783a64742e5ec5220cc667d599974724a5a76 +size 1016091450 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d74b87965a48cc01dda0cab128175fc209c6476 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4d9980868f9b685e760aaa6648281398e2489d699b6cdc97d10e0d72633c28e +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_500/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..131c59f885a56c1923a769ce99976e397dd87798 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb8153211f93f4ea2dc9a2063bb6dc85ba891ef881496d15a2ade1da297687f +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..b7ca83ba06571a5a970b6c04b0357a72871cb6ee --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b560608ab7fd1bee0b70507e0619cc6030d2c29f712a19bd5e124d2ecda553 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..cee4c6c1fc3f08d6cbf017231b81ff382034b6ad --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227f9183ea8d60b94f6b54a8a318de1c8957769108e66c44ae882e2a4d247869 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e738fa1d471ed6292ff49e81dc2ffb2f8419e38 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052fd1cd613af9d2a385c295bc2652726b7f8b1556b9f81f1264e344de0af052 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..af80aaaa71c4af1c5c15c271734492ee5f61a503 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90baf19713525ea3d26a1128cd8ab6c58f7df64008e6c28edc4da8eb6991d932 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..06458137a045b5cce2a86c2ae8c962c5a3fdee17 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7b1e79b42f2a03fce41c74d0f392d61c27fec4e87511b7a8db18a027304b635 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..19388ba2b38f8a72fd0ae47b6cc8e66a7fdd6317 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d7c10ada2613105e2a11c135caf774c1286f9a3b0726aae43f34a9bc204b72e +size 1016091450 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4bcf128dfa987e3d9c96262317dc9b0ec0e9130 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5692a7d664589b5d2b0a84606a75c4baedb0632e2dcf98b05a2636edfd9b0a8e +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_700/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_0.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b2b45a28c807b292bf6dccd8eab8e229e373e1d --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88f80cafc592e3a6aff5bd2e76e97cc4e19971ee21141e16f7cdabc428aa893d +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_1.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..b05a010161de95db9e6250a69d84efa2d1af2e32 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c29874a41fb44273ab51d0a539a022aada7093198b7c0ad445bba4e6359b572 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_2.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e9f6063c46136cfa41030da453470c68798fc15 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d7b45a1363f27ca13ce5afeffa914e9c40a110457d4fe4de0460efb867fd85 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_3.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1c7a16ffdf8e9cb055c683eeeabddc6d40847ea --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36b62bb8c4b240ac74d17e5f6b4a07d0c9e9f5f4a3d0c11a35c3cab07b22eea8 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_4.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_4.pt new file mode 100644 index 0000000000000000000000000000000000000000..c82226e7fbc9257b84d2747c7f542099232c747e --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_4.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a4bf67243ded38d710e9c870a7a1b6e2f7d69483bfaadae9686a07bce84d9c +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_5.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_5.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc641e88fbdbef96a62be6e6a7b389cf9a89d5b5 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_5.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f041bbe2b8601076fba182088c0a8c78994960ad70428bac09a9bd5a2f3a6c38 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_6.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_6.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1865fc282ddde6791ea3b0ffb8e34c1b95634b9 --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_6.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3a2bd0e6c355ab8676d5d44698f5f5c6c223d4c338a4ff34df7ad9b45edccc +size 1016091450 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_7.pt b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_7.pt new file mode 100644 index 0000000000000000000000000000000000000000..b64a07cb4182290a107e4b1a36e56a536358126c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/model_world_size_8_rank_7.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84c9ede3429b8517ebda6e9631df73d0240b238dd33d5aa21dfbf85bfcd9f9a6 +size 1016091578 diff --git a/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/tokenizer.json b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/MaxRL_Qwen3-1.7B-Base_IDK/tailrl_math12k_G32/global_step_900/actor/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654