Hugging Face's logo

FengdiFlo
/
Monte-Carlo-Q

Model card Files
xet
 Community
FengdiFlo commited on
Commit
461c718
·
verified ·
1 Parent(s): e8858b8

Add files using upload-large-folder tool

Browse files
Files changed (40) hide show
  1. .gitattributes +3 -0
  2. clip_0.2_grpo_r8/global_step_15/actor/extra_state_world_size_4_rank_0.pt +3 -0
  3. clip_0.2_grpo_r8/global_step_15/actor/extra_state_world_size_4_rank_1.pt +3 -0
  4. clip_0.2_grpo_r8/global_step_15/actor/extra_state_world_size_4_rank_2.pt +3 -0
  5. clip_0.2_grpo_r8/global_step_15/actor/extra_state_world_size_4_rank_3.pt +3 -0
  6. clip_0.2_grpo_r8/global_step_15/actor/huggingface/tokenizer.json +3 -0
  7. clip_0.2_grpo_r8/global_step_15/actor/model_world_size_4_rank_0.pt +3 -0
  8. clip_0.2_grpo_r8/global_step_15/actor/model_world_size_4_rank_1.pt +3 -0
  9. clip_0.2_grpo_r8/global_step_15/actor/model_world_size_4_rank_2.pt +3 -0
  10. clip_0.2_grpo_r8/global_step_15/actor/model_world_size_4_rank_3.pt +3 -0
  11. clip_0.2_grpo_r8/global_step_15/actor/optim_world_size_4_rank_0.pt +3 -0
  12. clip_0.2_grpo_r8/global_step_15/actor/optim_world_size_4_rank_1.pt +3 -0
  13. clip_0.2_grpo_r8/global_step_15/actor/optim_world_size_4_rank_2.pt +3 -0
  14. clip_0.2_grpo_r8/global_step_15/actor/optim_world_size_4_rank_3.pt +3 -0
  15. clip_0.2_grpo_r8/global_step_15/data.pt +3 -0
  16. clip_0.2_grpo_r8/global_step_45/actor/extra_state_world_size_4_rank_0.pt +3 -0
  17. clip_0.2_grpo_r8/global_step_45/actor/extra_state_world_size_4_rank_1.pt +3 -0
  18. clip_0.2_grpo_r8/global_step_45/actor/extra_state_world_size_4_rank_2.pt +3 -0
  19. clip_0.2_grpo_r8/global_step_45/actor/extra_state_world_size_4_rank_3.pt +3 -0
  20. clip_0.2_grpo_r8/global_step_45/actor/huggingface/tokenizer.json +3 -0
  21. clip_0.2_grpo_r8/global_step_45/actor/model_world_size_4_rank_0.pt +3 -0
  22. clip_0.2_grpo_r8/global_step_45/actor/model_world_size_4_rank_1.pt +3 -0
  23. clip_0.2_grpo_r8/global_step_45/actor/model_world_size_4_rank_2.pt +3 -0
  24. clip_0.2_grpo_r8/global_step_45/actor/model_world_size_4_rank_3.pt +3 -0
  25. clip_0.2_grpo_r8/global_step_45/actor/optim_world_size_4_rank_2.pt +3 -0
  26. clip_0.2_grpo_r8/global_step_45/data.pt +3 -0
  27. clip_0.2_grpo_r8/global_step_60/actor/extra_state_world_size_4_rank_0.pt +3 -0
  28. clip_0.2_grpo_r8/global_step_60/actor/extra_state_world_size_4_rank_1.pt +3 -0
  29. clip_0.2_grpo_r8/global_step_60/actor/extra_state_world_size_4_rank_2.pt +3 -0
  30. clip_0.2_grpo_r8/global_step_60/actor/extra_state_world_size_4_rank_3.pt +3 -0
  31. clip_0.2_grpo_r8/global_step_60/actor/huggingface/tokenizer.json +3 -0
  32. clip_0.2_grpo_r8/global_step_60/actor/model_world_size_4_rank_0.pt +3 -0
  33. clip_0.2_grpo_r8/global_step_60/actor/model_world_size_4_rank_1.pt +3 -0
  34. clip_0.2_grpo_r8/global_step_60/actor/model_world_size_4_rank_2.pt +3 -0
  35. clip_0.2_grpo_r8/global_step_60/actor/model_world_size_4_rank_3.pt +3 -0
  36. clip_0.2_grpo_r8/global_step_60/actor/optim_world_size_4_rank_0.pt +3 -0
  37. clip_0.2_grpo_r8/global_step_60/actor/optim_world_size_4_rank_1.pt +3 -0
  38. clip_0.2_grpo_r8/global_step_60/actor/optim_world_size_4_rank_2.pt +3 -0
  39. clip_0.2_grpo_r8/global_step_60/actor/optim_world_size_4_rank_3.pt +3 -0
  40. clip_0.2_grpo_r8/global_step_60/data.pt +3 -0
.gitattributes CHANGED
@@ -68,3 +68,6 @@ lambda_2_p-diff-adv/global_step_20/credit/huggingface/tokenizer.json filter=lfs
68
  lambda_2_p-diff-adv/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
  lambda_2_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
  lambda_2_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
68
  lambda_2_p-diff-adv/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
  lambda_2_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
  lambda_2_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ clip_0.2_grpo_r8/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ clip_0.2_grpo_r8/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ clip_0.2_grpo_r8/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_grpo_r8/global_step_15/actor/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8a4c59270b7a825ed63155c2c50e60a3ba988a5bd5cf2673840fb7a077b915
3
+ size 15205
clip_0.2_grpo_r8/global_step_15/actor/extra_state_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a57e0c792d3873bd9bedf6809d7ed9b97f61de98ecfdbe2a42bc3f1adbe995
3
+ size 15141
clip_0.2_grpo_r8/global_step_15/actor/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c533e7237757837a658c6d55a73a68c11a16649e2760c00190005151f0d75c
3
+ size 15077
clip_0.2_grpo_r8/global_step_15/actor/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95fc1320c5d26c40795429db357113d0cc7799eb61049826096c3a8048aff4f0
3
+ size 15205
clip_0.2_grpo_r8/global_step_15/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
clip_0.2_grpo_r8/global_step_15/actor/model_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bb1633c171eb4a1c61f34e237321ce034543f0bc210da03a4e0ec93ddec369d
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_15/actor/model_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:576dab608b4494da760154ae5add2131a1006dec35e5bf10c55f5ebc7fe6287d
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_15/actor/model_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe7918f67c554dbc63da4cfc57e63ad2099e048404cbaa67c482a826de38f263
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_15/actor/model_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9663a9a51e65825979da54521e1c38bc548bc45b57c4057dcb748f43f4a85061
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_15/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503ef7663d72891f010946b0ac033d1b63dc9986fc4eb795c26757190b99a8a5
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_15/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99c6943d9f47bce3087282be205cf70f937d90d48f6925783092fff8d5490a5
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_15/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:791031f9625c83aee8ebbdd07187660c0c78836a2ed7e4df25b57c30c6c08953
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_15/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2faf3178c83e9464992a96829cf344866f6fb8534ea7f6eae574c63b94eaee9f
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_15/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68327a52059597ba85f65ab836e7a77df0b6494467e0e569327bb0b154c29e68
3
+ size 7316
clip_0.2_grpo_r8/global_step_45/actor/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a79881a7c6bcb1ce31933f31ab5ed811b10232aa5cd278cdd0c0922e8c7223
3
+ size 15205
clip_0.2_grpo_r8/global_step_45/actor/extra_state_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b32ca4a88d751d2d9923e3ae04db5c028734eadb916ac81353d78601754a8c2
3
+ size 15141
clip_0.2_grpo_r8/global_step_45/actor/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a20e0aa3b9f3531b25b12ae946000edaff7f85b6d8654686cd8d5b89ecee5894
3
+ size 15077
clip_0.2_grpo_r8/global_step_45/actor/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4d8151feb5c75baa29446b54efffbebe1db0372d0462e77a6c954dcb50e31e
3
+ size 15205
clip_0.2_grpo_r8/global_step_45/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
clip_0.2_grpo_r8/global_step_45/actor/model_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75b3e3466152ee28e279e92f5d2d0e8c0f00059f5881d9078f3559bdf8968d96
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_45/actor/model_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf42833d85ec995b81b6f589c0a8ac9b6aff9cb6ddd97064b3400193e00a33d
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_45/actor/model_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578a164e3fedbef0386a8a92f9fd70652731f74df8b4e70e45a7d5c9a86b900e
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_45/actor/model_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02540671ec83b7d0956fc83744d29ad2699cda5a2681e1d8ecd55851bfdb38f3
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_45/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30213348ea23335e761dc0df796f235d40acc8f4342e9123a96b32c74707ffe4
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_45/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af6724839347807fe3e0c82df66ed61750731dbdef3ca510a99a14dbec31e8e
3
+ size 7316
clip_0.2_grpo_r8/global_step_60/actor/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f63fdc8a8a21ea186ad348e9eae65607810a85b266ad13f4e6278ab543b0139
3
+ size 15205
clip_0.2_grpo_r8/global_step_60/actor/extra_state_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276421567b81b31f4a68a8b0c6c95656224f718367fa97a48a9ddbb7b9985bbb
3
+ size 15141
clip_0.2_grpo_r8/global_step_60/actor/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3fcb05202e84922f67eb2b5ff9386b4bb51b61f1249e88f75db41cb60a97eb7
3
+ size 15077
clip_0.2_grpo_r8/global_step_60/actor/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262d31e3dbe56bb2f750b014575405e3c978747b591e91c364e11653f5dd9927
3
+ size 15205
clip_0.2_grpo_r8/global_step_60/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
clip_0.2_grpo_r8/global_step_60/actor/model_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23418775fc5404045c9b0fbcd1760f2594ac1e664ba22b1fba8e12464d6bc2d7
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_60/actor/model_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c765c63c3ad7e3cc9e0ae0102de6b5585c3930f701663d2f3054cdaf3e65b8
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_60/actor/model_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484c04f7f6d404d751aa840ec24505e5d4cce17bb08eccf6319428a589004908
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_60/actor/model_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e83eab370d7a41034bf92d6e599466d3e578de380a9d3a4c1a98d4d1fcf4f81
3
+ size 2031920747
clip_0.2_grpo_r8/global_step_60/actor/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb91ec87092eddd74c3bddfbfc9baeeea897628774f34f73f4fd08b72089bbf
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_60/actor/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab0b9eb98efe874d5a8679183d486f5c482cdc769d6e41841d5ea99a78cf7951
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_60/actor/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1cf2da695a0a07c4336f2b7e945ee39662bc641e531f55aa9680b2d0880259
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_60/actor/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f93803fec5aab3fa959a33f29f9259c6dd642a11f085429ab58bd87cdebc2ff
3
+ size 3441176616
clip_0.2_grpo_r8/global_step_60/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14996314da3c93e8954ba9d9fe0f1b540dbe85282da43550ccee2691df80f411
3
+ size 7316