diff --git a/.gitattributes b/.gitattributes index e1c9a61388384b329c8814a46f54d02b2015acd0..8199bd979e42a7d0fb620d145530d0e4003760ce 100644 --- a/.gitattributes +++ b/.gitattributes @@ -72,3 +72,32 @@ precise_coder_sft/4b-SFT-dsv4pro-1ep/global_step_41/huggingface/tokenizer.json f precise_coder_sft/4b-SFT-dsv4pro-hard-2ep/global_step_21/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text precise_coder_sft/4b-SFT-glm-hard-2ep/global_step_21/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text precise_coder_sft/4b-SFT-glm-1ep/global_step_31/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.5_run2/global_step_325/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.17_run3/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.67/global_step_325/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.17/global_step_325/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_up/global_step_225/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +old_template_backup/precise_coder/qwen35-4b-GRPO_0.5F1_min/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +old_template_backup/precise_coder/9b-SFT-glm-rl_0.5F1/global_step_150/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.33_f1ur/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_bcbfix_eagrpo/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k1.0_f1ur/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.33_f1ur_think8k/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/qwen35-4b-GRPO_unit_bs96_bypass/global_step_108/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_bcbfix_ugr/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.33/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.33_run2/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_bcbfix_k0.05_f1ur/global_step_325/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.83/global_step_275/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.0/global_step_325/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.17_run2/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.33_rec/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_bcbfix_k0.0/global_step_225/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.5_run3/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text +precise_coder/4b_rl_k0.33_prec/global_step_328/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_0.pt b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..11f972e0350508b92ce70c77804b7d6c24f42bd6 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3832fa9a9815347eb67dc3b4a8ebc4b5da1bc7ada5033dead04d2f7b0a51fc86 +size 14973 diff --git a/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_1.pt b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..705bfb7d1b1c33acdd83107c24d7b400f752f015 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3670beb3434ba57499ce317f79ac6ce47c69467fdbbe375a3dc41bb71b77b77f +size 14973 diff --git a/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_2.pt b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..49ab562a2a916cfd2f04b87af365c9b0c0790b43 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d565c3f01627026f552f2941759cff16d4c297daf1457c0d426604980eb4f1f +size 14909 diff --git a/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_3.pt b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9d5d5f9e7aff0016ef55177d0ef3e57947f2559 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd1c187eaac4fc8ce1d19d6971187b7e91c4932cd652627363a020df6194568 +size 15037 diff --git a/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/data.pt b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..3370e77258677c2d6e8b60202fe86771a4626164 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-27b-rl_0.5F1/global_step_328/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69749d09eb92e22048b4b490f91538a41e3b78c767524ac1c11b54e107579729 +size 7316 diff --git a/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/data.pt b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e1b2f3bc8b982e723b639d40ed5bc9d4b9d461f --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-dsv4pro-rl_0.5F1/global_step_250/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8606e90c79aba0fbe2bfe9e7d6aa9547be404e07225a2aef91f679d9ee96ee7 +size 7316 diff --git a/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_0.pt b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..0430eac045dbc030f5e0cab61a5389baadc6e73f --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b095545fed44d986f056974be9cf774e46b99b32ff08efa52a64369bdfa44d1 +size 14909 diff --git a/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_1.pt b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..a779bc5b9f01de0288a650549699f5edc7949c5a --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52b45d3f9e1a520badaecc5ca5b9be7a721f2b01ef5b9c6e7e058f48aeaf885 +size 14973 diff --git a/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_2.pt b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..70e39ff7c2d3b4a0bd53740f739bf7895dff1bb8 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348335efbf925ac0b8066db4185e12383ef0d7a43b1353f6c69bd909afe2b7f3 +size 14973 diff --git a/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_3.pt b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..5bb3dbd9c831523794d7bb033be2f250efa7c917 --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff84933f1bb3a7991803cd772d986ae23f80bf5489823fc8e89e3e0f7b05a6f0 +size 14973 diff --git a/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/data.pt b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d0a780a6141e3c8750e5cb83c6ffd59f06fdd5c --- /dev/null +++ b/old_template_backup/precise_coder/4b-SFT-glm-rl_0.5F1/global_step_300/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba50a13d118204a806312a5a26a0e30aee1e75fc850f09291db0e81a66a04553 +size 7316 diff --git a/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_0.pt b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..11c631de38fe01f0c3ea1a3585d51cc8528dbd13 --- /dev/null +++ b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7cb881c9a63a7dd8cb573655e841ac710bb2e53baf510a5083fd226cc306bf7 +size 14973 diff --git a/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_1.pt b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f0e4ceee4aa3f32204447647b1205826bf5dfb8 --- /dev/null +++ b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4849f0b39e0514e677deecb5c1edcb4cf5ce0000726ae1d6e8bdde2c4e8bb305 +size 14973 diff --git a/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_2.pt b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..763f5544efd00ad6c6a81eb61d1e82968e951d4a --- /dev/null +++ b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c75dcb43260cfec6d019fa305d1e74b0e3221e0f0a034637a4b475283d66a1e3 +size 14973 diff --git a/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_3.pt b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4e23d0329d3ee674963ef6774af2c9740a54ebb --- /dev/null +++ b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b66d04dd5acef56e3e16ffa4ac76bc8ac54ce59abbdaf11063b69811b37eda7 +size 14909 diff --git a/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/data.pt b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..8eafbced49f86a6da76baa7f3e6d00c1acdf15f4 --- /dev/null +++ b/old_template_backup/precise_coder/9b-SFT-27b-rl_0.5F1/global_step_250/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5b31052dfdac1195688d02ef7318f85e8af35ab7687228f8126d9097bf87b23 +size 7316 diff --git a/old_template_backup/precise_coder/9b-SFT-dsv4pro-rl_0.5F1/global_step_250/data.pt b/old_template_backup/precise_coder/9b-SFT-dsv4pro-rl_0.5F1/global_step_250/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..4817782fe5a10408b2f91932db9c35e87ab22889 --- /dev/null +++ b/old_template_backup/precise_coder/9b-SFT-dsv4pro-rl_0.5F1/global_step_250/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d77d8ff22a29d0a4583b77ebbf1fd5b6d102beab245d29fbab5dc379b3930e +size 7316 diff --git a/old_template_backup/precise_coder/9b-SFT-glm-rl_0.5F1/global_step_150/actor/huggingface/tokenizer.json b/old_template_backup/precise_coder/9b-SFT-glm-rl_0.5F1/global_step_150/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/old_template_backup/precise_coder/9b-SFT-glm-rl_0.5F1/global_step_150/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/old_template_backup/precise_coder/9b-SFT-glm-rl_0.5F1/global_step_150/data.pt b/old_template_backup/precise_coder/9b-SFT-glm-rl_0.5F1/global_step_150/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..291525fdb4943c8cf4c1d9fadc62f2fedf3b4fec --- /dev/null +++ b/old_template_backup/precise_coder/9b-SFT-glm-rl_0.5F1/global_step_150/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5334a66737e5f8b277ca495166f14cce68853c43a4a6fefba2180eb97d902cee +size 7316 diff --git a/old_template_backup/precise_coder/qwen35-4b-GRPO_0.5F1_min/global_step_300/actor/huggingface/tokenizer.json b/old_template_backup/precise_coder/qwen35-4b-GRPO_0.5F1_min/global_step_300/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-4b-GRPO_0.5F1_min/global_step_300/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_0.pt b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..3663fea746a099aefa03c97c83c787589c19fc67 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e2e901b20346415317de627fc23c96ea6844708f828bc0de8178c7c052e4dbc +size 14909 diff --git a/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_1.pt b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..eaa21bb985112d685bcdae947c57f2666e1f14aa --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9540acb64fbc6fe0641dfea9950e5363c847538d27a1d451b025159b5fd6cffb +size 14909 diff --git a/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_2.pt b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..f46b18d0cbde8a42ee5f1cb4b0a5094cb3efcae1 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66653a3527b4c224892e5ff3fc62e996fbd2aed95356b0a4b797fe42f29a6b07 +size 14973 diff --git a/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_3.pt b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..91401ee7a4e09495a325ca3300dfd592e2e0d9ec --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d4d0a5f595806a681bb9c4e20c6baabb30dc9c786a2991ce5eeb806de989f3 +size 14973 diff --git a/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/data.pt b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..f08acc49a392ebf2bff152a6e1caf55ba04c4820 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-4b-eagrpo_a0.8_b0.05/global_step_150/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b95461b05abd217e6c4dae90d9ea17aa8966828c6ce7eaa7a9a85c63ca7c601 +size 7316 diff --git a/old_template_backup/precise_coder/qwen35-4b-sftrl-rl_0.5f1/global_step_100/data.pt b/old_template_backup/precise_coder/qwen35-4b-sftrl-rl_0.5f1/global_step_100/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..820e94f22a6ccbd8c78276b9a26493252bd39154 --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-4b-sftrl-rl_0.5f1/global_step_100/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edfe7a1344c5e8a22e6a7923c2c8d58a610306ed78fc0bbb40bc0381f79ce8fb +size 7316 diff --git a/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/extra_state_world_size_4_rank_2.pt b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..e59337656afc39cd07b08b288fbabe25d0eedc6d --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cadf628dea80960258eeed6a6a8d9672f7a1a2a0254d299c8cea99a56933db7 +size 14973 diff --git a/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/extra_state_world_size_4_rank_3.pt b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..89605ab630699f6ccdc97b4b0edb08a20e178b9b --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc0c0d6e4434771996ba8ffb5f6b7163afc26bfe3a497b3eab18736d81e96b8 +size 14973 diff --git a/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/data.pt b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..f2de50bc1a996c406de873d76725ceb69068fe7f --- /dev/null +++ b/old_template_backup/precise_coder/qwen35-9b-eagrpo_a0.8_b0.05/global_step_200/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:993d143f9d7e37fe61c10073718aae897fb165d9c08e5d1d8f364ba3914308af +size 7316 diff --git a/precise_coder/4b_rl_bcbfix_eagrpo/global_step_100/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_bcbfix_eagrpo/global_step_100/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_bcbfix_eagrpo/global_step_100/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_bcbfix_k0.0/global_step_225/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_bcbfix_k0.0/global_step_225/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_bcbfix_k0.0/global_step_225/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_bcbfix_k0.0/global_step_225/data.pt b/precise_coder/4b_rl_bcbfix_k0.0/global_step_225/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0e842bc988fb39e14c948e7c35313ef264da0c2 --- /dev/null +++ b/precise_coder/4b_rl_bcbfix_k0.0/global_step_225/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7129bbb28d7f31ef80bbe2e34b335c387a9cdae4e38c24faeee87e6ce0197b37 +size 7316 diff --git a/precise_coder/4b_rl_bcbfix_k0.05_f1ur/global_step_325/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_bcbfix_k0.05_f1ur/global_step_325/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_bcbfix_k0.05_f1ur/global_step_325/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_bcbfix_ugr/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_bcbfix_ugr/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_bcbfix_ugr/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.0/global_step_325/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.0/global_step_325/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d1d0b3487dd8078ab8c665d0e4eb1e0bf97b8b5 --- /dev/null +++ b/precise_coder/4b_rl_k0.0/global_step_325/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e875a28b43afd0584f43460d91d96c96d6254240776ed0e5888f1f3bee2bd8f +size 14909 diff --git a/precise_coder/4b_rl_k0.0/global_step_325/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.0/global_step_325/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..9dba39cd0c9ad95c0fe3d2b372eef4dbcac84297 --- /dev/null +++ b/precise_coder/4b_rl_k0.0/global_step_325/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a63704a3a83e413d7dfa8a2a38740af8c3b873bff719b601be2567f2c8d413e +size 14973 diff --git a/precise_coder/4b_rl_k0.0/global_step_325/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.0/global_step_325/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.0/global_step_325/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..69fdaeed57ac08108b4fdd880c57f3c65eae3036 --- /dev/null +++ b/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c23b4a56dc36b63a9419885e1c7af011cb542a14d469083b2f536cd1a571b1e8 +size 15037 diff --git a/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..114c6ad2b2e26a70948276482d67ad87761255bf --- /dev/null +++ b/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e67a35e989f27402ce6c75e7db18c571577c8b91e726636386ca22d2c8e7c21 +size 14909 diff --git a/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..767f561a6e4c76e9e15f965cdec59d4005f3ffff --- /dev/null +++ b/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d514f81f7127fc0ca0d143bd93ecb4b6c3c1d23067e97b5b42fc68b36db442cf +size 14909 diff --git a/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..0477bbabbcc6ff82c45e85c2f1d3737ef4eb0bc5 --- /dev/null +++ b/precise_coder/4b_rl_k0.17/global_step_325/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5033e1d29460178e7159970808a6fdc36c722a5d95bb60f2408af479cb6770d +size 14909 diff --git a/precise_coder/4b_rl_k0.17/global_step_325/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.17/global_step_325/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.17/global_step_325/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.17/global_step_325/data.pt b/precise_coder/4b_rl_k0.17/global_step_325/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e3d51ccca0612d58368cd2afff6ff79f34958f3 --- /dev/null +++ b/precise_coder/4b_rl_k0.17/global_step_325/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65df088e564708487addfa964db6d87474ca07ca5ad302ad42bc1bc406b8e283 +size 7316 diff --git a/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..be29300b66e69e1ed42b158449586489672156cd --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d11c483647e6e90cc2f714ddf3fa1abb1f0331650a0b72de7e914a730d9782e +size 14909 diff --git a/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..45f97b26c6f07b7b6b56eec70c2459f4f6379afb --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5bdf2d890d5a4ffac94858b039ff870ce5831c68076669653ef5df308a24400 +size 14973 diff --git a/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..91dcfb75d4f1eb1ec3d800d0f3682dcb41e5d1aa --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e27919db68be63cae5ab584d24d3233e99894db30057b56459c967c6654a30 +size 14973 diff --git a/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..97e8a449059211d88dbe3b860560d3065289ed8d --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96e8912f27e77b6442b0d6b9ce1a49ef0682a77c14c23dc9c2561e5bbd50a90c +size 14909 diff --git a/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run2/global_step_250/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.17_run2/global_step_250/data.pt b/precise_coder/4b_rl_k0.17_run2/global_step_250/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc592e8caae7973a0ec58afb73476154edb6e760 --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run2/global_step_250/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2b6b815d37f7d3931b70e1aa727929f0873cda9de81007d85aba001dbeaaf0 +size 7316 diff --git a/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..ccc9ac1b66f19b6629255ce8044e18141d999f15 --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8684425ee3d1c9c9ff3da40259e54d0f07f935f823e0961207236b9969784e00 +size 14973 diff --git a/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf71b442b2912fcf90db875493a79241b233f668 --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1219678fa591d6988896b9635e9c8506e2c8dbe3f0ae411a79cd71bfc84b2674 +size 14909 diff --git a/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..4156c1b013f7dfaa86daaeaa957521f6e4aa9be4 --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2443ba7ddb80c820728cb0233bd26c5aebeca1e66d57dba677d5b42e2ac63f94 +size 14909 diff --git a/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..bacdd6af566f7bcbe37e12d74c4067e32be8185c --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6811ed3598496d58f4f29a30906cd902dbb558e7c64ac9c22ea28dbf5e396730 +size 14973 diff --git a/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run3/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.17_run3/global_step_328/data.pt b/precise_coder/4b_rl_k0.17_run3/global_step_328/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..493a2f2296272c466848821e62c580f7fa7cac6a --- /dev/null +++ b/precise_coder/4b_rl_k0.17_run3/global_step_328/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6619f84935fc94e0b0b4799894dfcb446355eff567a963b5b36cf5511825fa23 +size 7316 diff --git a/precise_coder/4b_rl_k0.33/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.33/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.33/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.33_f1ur/global_step_328/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.33_f1ur/global_step_328/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e58e66235782ff01ed591e36cfef5bf6563eec2 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_f1ur/global_step_328/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6f125c23d585559aef2dd11ec14916aae2d79ca90ce4154d4d2612772000d1f +size 14973 diff --git a/precise_coder/4b_rl_k0.33_f1ur/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.33_f1ur/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.33_f1ur/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.33_f1ur_think8k/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.33_f1ur_think8k/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.33_f1ur_think8k/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9fffe494fd0fa53098f0abc09298462c7a55453 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e2a8c4e84aa2205b23173c1b1b7052886d7551c4101a25873064f9aea96d29 +size 14973 diff --git a/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..091a20d70781d42ca432d5b52a0bbc4557794ce4 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d554b48adbc042c8bc61f4f5c1546c3b1cc33f79c83ee60f67f65f8d94eccc4b +size 14973 diff --git a/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/data.pt b/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..107264c225e540f3976a5332ca897471faf44d09 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gated_v2/global_step_275/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c450f10493e4e46b8181c64f401034088f136e11563a491d5772e488a6edd7f7 +size 7316 diff --git a/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..e8938695ea44e4cc87c069a9e18f8db9a94d4eba --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee28969a655832b749fd3484932d2c193b898aeca702ba9332ea3f780768c34 +size 14909 diff --git a/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f4d903fe004191539c54537d2ee631d70825502 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbe3aba5d5b8a8a409844018577feeb1596c38d2c34690df5ccfe3c0b00c685e +size 14973 diff --git a/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.33_gdpo/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b6910f12efe36a603b392d1152830cf43e15b73 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5845313b66d492c00137868fc0851313b96aa262bd128020009856c2547236d3 +size 14909 diff --git a/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..c333c003360f1e23f708ffb17c68e746ebbb873c --- /dev/null +++ b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:859918dbf2439590e23c9bce2393593d0ba00a9cf7af59cf5d69bdaeefbd3a94 +size 14973 diff --git a/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..042f651c7ddcaf6eeb50d9d3807827aee471d39a --- /dev/null +++ b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c2c827908fc12f71dc640247d5db5d37752a6424025fa3048de99b882508c7 +size 14973 diff --git a/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a8b4e34818d80b3985bc14473388aa43ebe0070 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dcfa96feffd0b3b628c1d2dcfa401686f3e9ae4b4ea67822992728fbebb61d8 +size 14973 diff --git a/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.33_prec/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.33_prec/global_step_328/data.pt b/precise_coder/4b_rl_k0.33_prec/global_step_328/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..d511dc0c67ab9fddb8ff8814c789534ca0b8c318 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_prec/global_step_328/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06fb0803cad7d9fa9a7c4a46099ee917a59558dba8e401da84e874905c89a802 +size 7316 diff --git a/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..c93f86079f57da64fcdf0e4bdfddc203c34bba2b --- /dev/null +++ b/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88887a4a5bd875b078378e4dc0b7e246bbe153554c195ca78023c0d13fc87c12 +size 14973 diff --git a/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..37ce35b8e7455ad03ff2d192acc14954d8ce973d --- /dev/null +++ b/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b484da254fcac066c95b8fb600d4c4964ccf01615e6195b1e9ec7a07e0cef44 +size 14909 diff --git a/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dece1a5e405aaa52b496a5627b1844713339368 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b79ada45cd83bca51da5886b54903b7e41ba4d5faef339a385e06f491497a9 +size 14909 diff --git a/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.33_rec/global_step_250/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.33_rec/global_step_250/data.pt b/precise_coder/4b_rl_k0.33_rec/global_step_250/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3deaacb10e5838b20a929d3fe3161d49e7cf15d --- /dev/null +++ b/precise_coder/4b_rl_k0.33_rec/global_step_250/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:897fe3d1c676c9e6be250f62b0e770ae88b19d1de22875e85834593539a341a8 +size 7316 diff --git a/precise_coder/4b_rl_k0.33_run2/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.33_run2/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.33_run2/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8f86e68499974695d3c18d6296bb530863a06d7 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa89c3e7e7a854dd400d852557c29852a4f8c38b9e5d34f46adcd05388011985 +size 14909 diff --git a/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..74c521c13cbab8b23d9d7751972d0a67a96bf1ee --- /dev/null +++ b/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1803ae77cde44339117ef030b2ed98c74da012e39cc1a2b6e4babe69010b14 +size 14973 diff --git a/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..769290f894cfca56c1ff59e24982c9fd1b89b2f9 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0875ed1617056a1a5b675211e33c06468d5bbec509d3a4092cdb509d26b392d9 +size 14909 diff --git a/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..18fb689c5651b9d752d86c4b32c1e28d4779ea5c --- /dev/null +++ b/precise_coder/4b_rl_k0.33_run3/global_step_175/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4277b84aaf1e481352a2fd45136d38ee99acf3609de02a3ba3c5f96d00afe482 +size 14909 diff --git a/precise_coder/4b_rl_k0.33_run3/global_step_175/data.pt b/precise_coder/4b_rl_k0.33_run3/global_step_175/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..7335c1060654f155a4b0e05ddf6fd43b6bd94028 --- /dev/null +++ b/precise_coder/4b_rl_k0.33_run3/global_step_175/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80f7d21949170c222588fe59483c744999d381b28333d0fb704146c74127d2cf +size 7316 diff --git a/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..52ded4dbd416f24f5453ee7506cf0098cc73df73 --- /dev/null +++ b/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31433596b996d32e140a79f7aa33182df68281a31d3f4c5646142e73e4331e23 +size 14973 diff --git a/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..118587685516f16562a8c317ab5c48dd15adec56 --- /dev/null +++ b/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4803998f77a453c4709fdc2aae082b1e5d4588120ac968e7baaa16cc8a0e33 +size 14973 diff --git a/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1b13345b9ce971d6272337550478b158dfb68ae --- /dev/null +++ b/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a66417a28cbc76c1131c0c0a142f5ede4d17e5e058054ea98622deaea8835a3 +size 14845 diff --git a/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c4090f60d24a4474111be9ee2eb25f38cacca4d --- /dev/null +++ b/precise_coder/4b_rl_k0.5/global_step_275/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43316272ab7d0e6a3725b14d124fd23a3fed1a67279b82ee1e27ccb71152b1eb +size 14973 diff --git a/precise_coder/4b_rl_k0.5/global_step_275/data.pt b/precise_coder/4b_rl_k0.5/global_step_275/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..511e90806682a70275a140df35102449b279e310 --- /dev/null +++ b/precise_coder/4b_rl_k0.5/global_step_275/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97240640e29fb952dedd0fb340dfabd52409ae5b0424651f5b57830da7c1e96c +size 7316 diff --git a/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..4620204557c0e1e3b0138df49f9faa755bc4935e --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ccb37ff08d533eb3c45491eef780f0482e9497707ca109e678c500e196b21ea +size 14973 diff --git a/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..85d09f694c7f98ab7d6fdfe3ec4909b372e82090 --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ccdb7a2e65e8a91803b028e2c3ab799c10a6dd9f3f2de19bc79945d576dc91 +size 14973 diff --git a/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..4bdddb1f1a4a721b1caaf8f0c48ff59ccd9075a1 --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60641457696a3b9c182ab272262eceb64d913a609e5494d802ddf8b6c5c4afc1 +size 14973 diff --git a/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..a410f5fd0c464fd115b44dfd4bd86c653ea1486a --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94142a5fa1887e2b3aaeab16b4d47462e4a176ecb038afe3c25b235cf8a08d93 +size 14973 diff --git a/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run2/global_step_325/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.5_run2/global_step_325/data.pt b/precise_coder/4b_rl_k0.5_run2/global_step_325/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..563656c881b993f9974848901a55db141bb67327 --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run2/global_step_325/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319bfed81a9dd0bd1817817ff823d88e23c5f7a57d63b3018c192ce39e46f2e3 +size 7316 diff --git a/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..915a3e8133502a414415a284b59b6dae7a407190 --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46153ad601186eb00c5c2d7d80ae8f8c0a62849828ed236244ba9fd5d2783c32 +size 14909 diff --git a/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..779f7544b58e01f77d30c53706d2444246f4c29c --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d42ed429e7ae949a15ea96bc4db5d6df3e66ace9c2049121e0a0776748e16bd +size 14973 diff --git a/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6612090406380f92c5954a86375d19b61ba5a79 --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa52d5f2b078874769349155402881f71b1c798476c3a25128d5b4513a8eb3c +size 14973 diff --git a/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..6674e1d6a819b242ccc4e35645f4bbb9826d6baf --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af05e59f7586a26397f450c9babc5270ae60da5b56ee8420b7d2296eaf5b5c62 +size 14909 diff --git a/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run3/global_step_200/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.5_run3/global_step_200/data.pt b/precise_coder/4b_rl_k0.5_run3/global_step_200/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..29ef20c0a5e917d9cad3efdaf2fab217334e6915 --- /dev/null +++ b/precise_coder/4b_rl_k0.5_run3/global_step_200/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b69d35c9ac8b2e973ee5840a9c57e8d0f286e1966fd31ff396d61d46659bb58 +size 7316 diff --git a/precise_coder/4b_rl_k0.67/global_step_325/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.67/global_step_325/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..252480b994d1db3dea7e359dd07d358b901fd2a3 --- /dev/null +++ b/precise_coder/4b_rl_k0.67/global_step_325/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0c5a9f04dcb6e1e5a54324a5fc85a7a9cb203b61cbc1b5dd6d4f5488df277e +size 14909 diff --git a/precise_coder/4b_rl_k0.67/global_step_325/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k0.67/global_step_325/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f8d00841fdb66d5c492f9de57b1b6801316eef3 --- /dev/null +++ b/precise_coder/4b_rl_k0.67/global_step_325/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9c0f485ef6b56d1f1e1700f473078150c27545073771c2ec28e141cc092fa8 +size 14973 diff --git a/precise_coder/4b_rl_k0.67/global_step_325/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.67/global_step_325/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.67/global_step_325/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ff3002be008f58f7e4e677e59aa277aaa109ef1 --- /dev/null +++ b/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4952f2b16e0063ca98db12bf34bbb09a71ef90b016a8db1dd332c908affcb4 +size 14973 diff --git a/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..73989d8b373b722d42b63c9ad9df7edabfeb5ab9 --- /dev/null +++ b/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54343137c0ae06561e068cf3d8461cdbd0babd646bb3e9b0d180da20928f1d0a +size 14973 diff --git a/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4846e7289d214d113b1d48fbc5c37e17f5b9b93 --- /dev/null +++ b/precise_coder/4b_rl_k0.83/global_step_275/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ad90b9fa741e1e1d71353b4321dcb682ae7b587c8c5952a93069044134af616 +size 14909 diff --git a/precise_coder/4b_rl_k0.83/global_step_275/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k0.83/global_step_275/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k0.83/global_step_275/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_k0.83/global_step_275/data.pt b/precise_coder/4b_rl_k0.83/global_step_275/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ef22b1b2e12ee64fce7acc709944844a5b20bda --- /dev/null +++ b/precise_coder/4b_rl_k0.83/global_step_275/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f6c530833034389683d320db9bc6474c675a899b1376b455aab12db59ae106b +size 7316 diff --git a/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..77f6128c3c41ad94ae837b11c4e32acae41baf22 --- /dev/null +++ b/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5f5b1cd6a9b6300b08c610251b4901e77c92c6ff54df0457395203f8047790 +size 14973 diff --git a/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3bc29ef9e96b64eba59f244cc81d364c73d45c6 --- /dev/null +++ b/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74672fb83a13cb01617108229b7d0ab7d2a20f2c419f2c227bb2ce970a278180 +size 14973 diff --git a/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..42ad5450bc0eefb3030cd7b2f30a154a8dd3c928 --- /dev/null +++ b/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:929bb5a5e87f61285e500b62ba4bda8054281d0b7da74ff9ef59a2e2d458556d +size 14973 diff --git a/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b5141fd89324acb2715d917469f0f97e3081e56 --- /dev/null +++ b/precise_coder/4b_rl_k1.0/global_step_328/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdbfa7d65a06d26e05e628fa9f679bbc25d23ee30fb2673dbc27206cf99311b8 +size 15037 diff --git a/precise_coder/4b_rl_k1.0/global_step_328/data.pt b/precise_coder/4b_rl_k1.0/global_step_328/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..abf4d538944f8fa13683c289fcbf2bae1209b85f --- /dev/null +++ b/precise_coder/4b_rl_k1.0/global_step_328/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5cb39b3e64b3af54f851e10d4e6850c15373b78e1f1993e8ff592c3281a4805 +size 7316 diff --git a/precise_coder/4b_rl_k1.0_f1ur/global_step_328/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_k1.0_f1ur/global_step_328/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_k1.0_f1ur/global_step_328/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_0.pt b/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_0.pt new file mode 100644 index 0000000000000000000000000000000000000000..2715b67647209f758a4f12fd696a769381591bcf --- /dev/null +++ b/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_0.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8937847dd9ba453268fa361bab12fdc046b2552e92dccffd3e21ffaf23b8c23d +size 15037 diff --git a/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_1.pt b/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_1.pt new file mode 100644 index 0000000000000000000000000000000000000000..eac82e38e9160a29e7e7dca21f07c01a6e4a354b --- /dev/null +++ b/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_1.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56004d62f96f029127d366b99fe721b4a7a9d505308d63c8e9ae502449743a2a +size 15037 diff --git a/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_2.pt b/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_2.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6bbfe4d334f30503d732462f3e273ef6966726a --- /dev/null +++ b/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_2.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbca010c999979d111ebcc11bcb739c991bc2c4f3f547f4ccd08aa0f4df46a8b +size 14909 diff --git a/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_3.pt b/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_3.pt new file mode 100644 index 0000000000000000000000000000000000000000..197629a3122b9f0cb9fdbc4eeda071dfc7e78e38 --- /dev/null +++ b/precise_coder/4b_rl_up/global_step_225/actor/extra_state_world_size_4_rank_3.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7d68e6b3c2d4a0a296266e07c99085d7991c8354731ac410dee2d9402aa397 +size 14973 diff --git a/precise_coder/4b_rl_up/global_step_225/actor/huggingface/tokenizer.json b/precise_coder/4b_rl_up/global_step_225/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/4b_rl_up/global_step_225/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder/4b_rl_up/global_step_225/data.pt b/precise_coder/4b_rl_up/global_step_225/data.pt new file mode 100644 index 0000000000000000000000000000000000000000..0321af18db9045a6792ed70c424f472c84ff3066 --- /dev/null +++ b/precise_coder/4b_rl_up/global_step_225/data.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155892490bd21f821417397ff4c7114d328221d7fd3ae375548c01323d32b8ce +size 7316 diff --git a/precise_coder/qwen35-4b-GRPO_unit_bs96_bypass/global_step_108/actor/huggingface/tokenizer.json b/precise_coder/qwen35-4b-GRPO_unit_bs96_bypass/global_step_108/actor/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder/qwen35-4b-GRPO_unit_bs96_bypass/global_step_108/actor/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/tokenizer.json b/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder_sft/4b-SFT-27b-1ep/global_step_45/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/tokenizer.json b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-think7k/global_step_29/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/tokenizer.json b/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackA/global_step_28/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325 diff --git a/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/tokenizer.json b/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5520bfd2dd834ce386c1312c410fa71af56db5ad --- /dev/null +++ b/precise_coder_sft/4b-SFT-rej32-trackB/global_step_39/huggingface/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 +size 19989325