Hugging Face's logo

FengdiFlo
/
Monte-Carlo-Q

Model card Files
xet
 Community
FengdiFlo commited on
Commit
17e56ff
·
verified ·
1 Parent(s): e5ff0f9

Add files using upload-large-folder tool

Browse files
Files changed (43) hide show
  1. .gitattributes +4 -0
  2. lr_1e6_kl_002_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json +3 -0
  3. lr_1e6_kl_002_p-diff-adv/global_step_15/actor/model_world_size_4_rank_1.pt +3 -0
  4. lr_1e6_kl_002_p-diff-adv/global_step_15/actor/model_world_size_4_rank_2.pt +3 -0
  5. lr_1e6_kl_002_p-diff-adv/global_step_15/actor/model_world_size_4_rank_3.pt +3 -0
  6. lr_1e6_kl_002_p-diff-adv/global_step_15/actor/optim_world_size_4_rank_0.pt +3 -0
  7. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_0.pt +3 -0
  8. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_1.pt +3 -0
  9. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_2.pt +3 -0
  10. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_3.pt +3 -0
  11. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json +3 -0
  12. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/model_world_size_4_rank_0.pt +3 -0
  13. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/model_world_size_4_rank_1.pt +3 -0
  14. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/model_world_size_4_rank_2.pt +3 -0
  15. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/model_world_size_4_rank_3.pt +3 -0
  16. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_0.pt +3 -0
  17. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_1.pt +3 -0
  18. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_2.pt +3 -0
  19. lr_1e6_kl_002_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_3.pt +3 -0
  20. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/extra_state_world_size_4_rank_0.pt +3 -0
  21. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/extra_state_world_size_4_rank_1.pt +3 -0
  22. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/extra_state_world_size_4_rank_2.pt +3 -0
  23. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/extra_state_world_size_4_rank_3.pt +3 -0
  24. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json +3 -0
  25. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/model_world_size_4_rank_0.pt +3 -0
  26. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/model_world_size_4_rank_1.pt +3 -0
  27. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/model_world_size_4_rank_2.pt +3 -0
  28. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/model_world_size_4_rank_3.pt +3 -0
  29. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/optim_world_size_4_rank_0.pt +3 -0
  30. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/optim_world_size_4_rank_1.pt +3 -0
  31. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/optim_world_size_4_rank_2.pt +3 -0
  32. lr_7e7_kl_001_p-diff-adv/global_step_15/actor/optim_world_size_4_rank_3.pt +3 -0
  33. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_0.pt +3 -0
  34. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_1.pt +3 -0
  35. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_2.pt +3 -0
  36. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_3.pt +3 -0
  37. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json +3 -0
  38. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/model_world_size_4_rank_0.pt +3 -0
  39. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/model_world_size_4_rank_1.pt +3 -0
  40. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/model_world_size_4_rank_2.pt +3 -0
  41. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/model_world_size_4_rank_3.pt +3 -0
  42. lr_7e7_kl_001_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_1.pt +3 -0
  43. lr_7e7_kl_001_p-diff-adv/global_step_15/data.pt +3 -0
.gitattributes CHANGED
@@ -151,3 +151,7 @@ lr_1e6_clip_35_temp_1_1_p-diff-adv/global_step_30/credit/huggingface/tokenizer.j
151
  lr_1e6_clip_35_temp_1_1_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
152
  ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
153
  ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
151
  lr_1e6_clip_35_temp_1_1_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
152
  ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
153
  ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
154
+ lr_1e6_kl_002_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
155
+ lr_1e6_kl_002_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
156
+ lr_7e7_kl_001_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
157
+ lr_7e7_kl_001_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_1e6_kl_002_p-diff-adv/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
lr_1e6_kl_002_p-diff-adv/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 sha256:3e480540d1a7f2ea9d8ddb2f0ae163a90b6ba9f433b184ac61bd452a5622f909
3
+ size 2031920747
lr_1e6_kl_002_p-diff-adv/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 sha256:71b8ee25138e5368570d3f8b011b6f5311831d5ff7e715c1369f02c200a8c21a
3
+ size 2031920747
lr_1e6_kl_002_p-diff-adv/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:c1db572048abef04095908ce2e66bfa0b701e89721f6b25c5686eca8f8b7078a
3
+ size 2031920747
lr_1e6_kl_002_p-diff-adv/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 sha256:115e97055d3de0e231ad8871f8f4ccfbe1297d5e29922d5c4b83026031d25d8a
3
+ size 3441176616
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36cbea5183afa642fc0a949443d762d9597c80dafe2f51d2f43d5d9694080600
3
+ size 15205
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/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:eebc1839080ab90d29193ae71281a72ad7da2b894ef1d287431f89a386d6c6f2
3
+ size 15141
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307b8569eaad82b8681c5f9096831804334c490cf9d21db00766655403364c0c
3
+ size 15141
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62292cefb9a05088ce041b3ffe7c72c3e9de14bd8b76e57209c490b71c163396
3
+ size 15141
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/model_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4628e1bc8c7c2a7382a67b34b2648c50bab0fc831b1c7d025655d6ee614aba8
3
+ size 2031944043
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/model_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbe3dab83c783a6f1f81fcc8ec14f2b7286a809ed40064a962cba0ba81e46f8
3
+ size 2031935851
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/model_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfc6c2cd9c79963a41891b7f0e319c524d13f248ae91565f1776bf2799860af
3
+ size 2031935851
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/model_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a61f1b6b5b42339c20443b4b1ab1b8f3df52dacf40777b9d28d8d33d1c111e79
3
+ size 2031935851
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b9680fd7a1cd25c413b1e9155c7f962683955f3fa03014d49124470007693b
3
+ size 3441180712
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d472dcba87aa7d3d991ceb6021e894f688e74fb5177692f45b8a4494ec41817
3
+ size 3441180712
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cdc4225bca08b249d2919f4e518216721cbc407a4fb2e1b515265b1cd4f5d6f
3
+ size 3441180712
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd71cfa8718071082cb189bc0affcd4bf5de1635d5435a2ee5955d319c47d64
3
+ size 3441180712
lr_7e7_kl_001_p-diff-adv/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 sha256:456f502a5f7062dccd68a0d4df9b8c9e416b9109ff309900650c58c448ae2f86
3
+ size 15077
lr_7e7_kl_001_p-diff-adv/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:a6d8e625f81427777eda0bc1091202a4fbe1e28d4282f5fad996dc81edac654b
3
+ size 15141
lr_7e7_kl_001_p-diff-adv/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:d5f2e45099f03dcabf975ffeef62d18d9330eb3f058f24fabf55d4b4e099e80f
3
+ size 15077
lr_7e7_kl_001_p-diff-adv/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:c64d95d0f29f8738328cfbbf4ea0c4ba8ea6abc5a307cf6af8f38505d8986f5f
3
+ size 15141
lr_7e7_kl_001_p-diff-adv/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
lr_7e7_kl_001_p-diff-adv/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 sha256:64edbd16f51d36428ac2d79990683f79b8966aa1a61bdf590a491f0d30aef6a7
3
+ size 2031920747
lr_7e7_kl_001_p-diff-adv/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 sha256:3c49e8fc71399698ce79118879459bb669f72fbf8995cd95c3ef9e5c982dbf56
3
+ size 2031920747
lr_7e7_kl_001_p-diff-adv/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 sha256:0c99f0453c2d84769a35579288303ad62b3affa2374e291553e768be920cbe08
3
+ size 2031920747
lr_7e7_kl_001_p-diff-adv/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 sha256:3f7538cc9064dc1953fee7fbfac79d507c73647c206bf566e6ed3126563410ba
3
+ size 2031920747
lr_7e7_kl_001_p-diff-adv/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 sha256:38ae85190ea7cd8cc0abed7138114ee972a5ee144ffe129e0fcb555fee7e7d3c
3
+ size 3441176616
lr_7e7_kl_001_p-diff-adv/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:b3408f7d3ea822c1cc491570ce49999a0e2a65627c072c5356ee1cffa9fb1a85
3
+ size 3441176616
lr_7e7_kl_001_p-diff-adv/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 sha256:0748ee73c163fc16aba25e3dc9c5e75d61e1c25a1071227356b498d09c693e41
3
+ size 3441176616
lr_7e7_kl_001_p-diff-adv/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 sha256:26344ea6e491e28345719b6d30c5cfef9c022ad143e878b2c87bd7f6bd5f6ab6
3
+ size 3441176616
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7b8ef7eb5a4aa9f5a3b97e42eb077b405a9948a0d86c8473c1de57486fe1ca
3
+ size 15077
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/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:c730f2302c1c294b7230017cee79b8292571e854048afa51e50b8f7931a1b494
3
+ size 15141
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168b683ac26cf42fe9e8c7543ec5f9775da8a444479563b02a54743dbd449308
3
+ size 15077
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/extra_state_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:168c2fa29c1562baf61cd2e5ce854d92c88fdb4fc5dd6b77bf01c6768ace1b1c
3
+ size 15141
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/model_world_size_4_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec55fe911a0cfc20770cda962eab474b0d038e1f157bc8c2de0e8acbc8a111b
3
+ size 2031944043
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/model_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c20bbf91b739a5911b0ec24445b6ab14e21f80ca4f62edf76dbe205649b141
3
+ size 2031935851
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/model_world_size_4_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98669e492e09341843f846334c1910e521f8d6197ee89c8288128859380ff5a3
3
+ size 2031935851
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/model_world_size_4_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0ea581212223f47cbddaf5f9f0262808f66623350fe4ae92e30b1c0db3b287
3
+ size 2031935851
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/optim_world_size_4_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461772de5772dc4b3e6d99f1dc247179f045cf09cf9e59ebc9f44cc5b87795b7
3
+ size 3441180712
lr_7e7_kl_001_p-diff-adv/global_step_15/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3083ef7570ca612b7d460ff12823aae2768408646bb1164bec779b22e77e585
3
+ size 21489