tyzhu commited on
Commit
e80fc60
·
verified ·
1 Parent(s): 25ac813

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_0.pt +3 -0
  3. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_1.pt +3 -0
  4. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_2.pt +3 -0
  5. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_3.pt +3 -0
  6. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_4.pt +3 -0
  7. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_5.pt +3 -0
  8. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/huggingface/tokenizer.json +3 -0
  11. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_0.pt +3 -0
  12. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_1.pt +3 -0
  13. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_2.pt +3 -0
  14. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_3.pt +3 -0
  15. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_4.pt +3 -0
  16. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_5.pt +3 -0
  17. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_6.pt +3 -0
  18. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_7.pt +3 -0
  19. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_0.pt +3 -0
  20. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_1.pt +3 -0
  21. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_2.pt +3 -0
  22. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_3.pt +3 -0
  23. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_4.pt +3 -0
  24. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_5.pt +3 -0
  25. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_6.pt +3 -0
  26. mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_7.pt +3 -0
  27. mathmedium2-grpo-qwen3-1.7b/global_step_100/data.pt +3 -0
  28. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_0.pt +3 -0
  29. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_1.pt +3 -0
  30. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_2.pt +3 -0
  31. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_3.pt +3 -0
  32. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_4.pt +3 -0
  33. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_5.pt +3 -0
  34. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_6.pt +3 -0
  35. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_7.pt +3 -0
  36. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_1.pt +3 -0
  37. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_2.pt +3 -0
  38. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_3.pt +3 -0
  39. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_4.pt +3 -0
  40. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_5.pt +3 -0
  41. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_6.pt +3 -0
  42. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_7.pt +3 -0
  43. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_0.pt +3 -0
  44. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_1.pt +3 -0
  45. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_2.pt +3 -0
  46. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_3.pt +3 -0
  47. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_4.pt +3 -0
  48. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_5.pt +3 -0
  49. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_6.pt +3 -0
  50. mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_7.pt +3 -0
.gitattributes CHANGED
@@ -90,3 +90,4 @@ mathmedium2-mutualposclip0.5-qwen2.5-3b-oldreward-corrupt-0.1/global_step_100/ac
90
  mathmedium2-mutualposclip0.5-qwen2.5-3b-oldreward-corrupt-0.1/global_step_200/actor/global_step_200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
  pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge3-temperature-1.0/critic/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
  pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge3-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
90
  mathmedium2-mutualposclip0.5-qwen2.5-3b-oldreward-corrupt-0.1/global_step_200/actor/global_step_200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
  pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge3-temperature-1.0/critic/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
  pilecc_cont1-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge3-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
93
+ mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc14f7204d6fc130f80c7bb6c4fd804b5e96a573a6224859212e7c211ea6f90b
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27f2106ba6c26ef193b5d0577e329d7632aa829078556aed896a29ddf6d92ad
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6638977110689fa355fde4b7aa94e0caa05f8ff69807ca9ddbe603a9c00ab6e2
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54627ca22a11e38f4ab7e818861d9ddbfafb41a4a4354764040f25e37962ed87
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad26d3d8a77527068885415f0fe20377f2d4e201d2db2dab981bba744b38b64d
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084648afa1455fb04eff004a007db3e696475202a53e64a5bcc906d756537812
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbffdf595550026d97c55e05f352e09fd9c35344fc2587fb372a32923fca2ad2
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f55abcbb8552bb0a36fed723a5187a61123d2865f8392a01215418a759a665
3
+ size 14632
mathmedium2-grpo-qwen3-1.7b/global_step_100/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
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19750420b2c425b72955788d6eaeb8e8d940f849992e2e0abb04a1d4504c1aa9
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ed06d91c3622921bb337530e845beb9910015b75640c613bffe2a4fd25f0d5
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7134382291ed8d8905984783de0493639d918a6d689057d17f5713d3dffd056c
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87184fcdbec717490d5f9e84e92388c4b18ed2bf059cc3bbec908ab5b4e77777
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45436ca4d10cd29937490c8baa4d685d4b0a3cd27043dba858bb1817c4397199
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b91c5adf5b3f98da1384d1fdb5a0c65f0d204271319f53b8758868d57830a82
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7a03ab6f66a051f70892d02341633f5df30b2c931bad936d903b7e44a605df
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de49327a63f5af46d7cc316445b98988e2a0da6d4a435553ec829224a353cb68
3
+ size 1016051898
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017d3037c19fcbd47ae6fcbc06c936f3508e92cc50b55c6b8b9e2f273d963534
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b6dc7df1336a4945dedf2a74050c9f3c229fb73b59ba5bd1bf1b5291b97488
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9117d36bc0ebeff7640061d99d3f64f65d919d049229940174b29a49cef9095
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9eef8939dbbbc6fa4014ddac66712a47317edbad2cdd3b2156862b9baf3c1f
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c865237de33b0d9a147f099e121f6e5d0e27a6688dbe06a106b85916aa5a1c46
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab3ece9bf7edd2ded8efe59782938917d5bcd86966eaccb19eed846614ff06a
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9224f030bbcda6d76b07179736f7f6cede703f374b7fa98ea957fd18840b3aa1
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b/global_step_100/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365b84e937d7719efc7bd497c76199b342aeea92540a501204a2b81ca7900d6b
3
+ size 1720600311
mathmedium2-grpo-qwen3-1.7b/global_step_100/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b026a92967a08ac24d2ab22b2f9064818034ca6a43f66c7503d070d12ccd865
3
+ size 1492
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e6e1a88745ff2cc998e39f3a0452cde469b60c5cb71f2dd299256b4fdd8bc4b
3
+ size 14632
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f3a8dd67875269f519007fb0f201019aa640880d7a0a7dfeefc4e4bf718083
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b884f1ca9d76915ecba65df6c5809703f782209f93572d4ca37399ed4b5aaad
3
+ size 14632
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d6d6eaae868877247a6950f50c3a97057e14ab9071b9be91efac76318a9ada
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff238af807b24146b5f3a0e859d343e760a17e41199012b7f2d5cf5af53ad55
3
+ size 14632
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f98ff9e138d90a2b959c847d80593afcb42d20cc72261757fe367c9611b8ca3
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75a11705e6f1beaf96aaefd0f519e1fb840720a50aa6ad7cfc9e41d558b3a44
3
+ size 14696
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300f6583060851b226220281b40297632c124c2a093aba9510e9b80ac41ac256
3
+ size 14632
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34a447a1cb927b02344f72e9680c350b658bc464a4f2fa37a59687ed9ffc50b9
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a8509627f9c0886e1b4fd6667245568f529637e5bec36e8218834610f728ff5
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d538cfe9afbf96ce35f733c96ca9184f149bee7e90c666a9c64dfc99606f430
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f05a966439e72a6ecf8c2e0ada4b6f3699f255f1fc1e8382aa1e0abd33cc969
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9bcaedf4ebb4826f67346af450d0e470fa7d1076e100b92ba290e61045bcc56
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca5a9805e364ec9165e401b9ec78109c0faa1bdd8f4808805b6fb36e35ea3a2
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2e91b227688d50af02138595f8865592b574922b03bf84a10a53f19a84ebb2
3
+ size 1803528186
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac16cecad302c4cf4ad46861f093e2974a8de230d1db5a6aab77b649646e9bc
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:211be9e485d4dd3ac99cd44438c8e6827c0a1beb7d6c583c484591fe05f0c41c
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64226059ef2f5457374b202f11b0fb7f4ac8ac600b7c2ae3744a36f83d0913dd
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14565667e007e8bfd8c1068de70090edd945f48ffaea01ad7035ad4b8d6f84c
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb84929c014ae87f7b58de377b3531add4a59355f5d0ede545c1f7b4ba8cfd1a
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2221e6ce5dd80b0fd9f2aaa9957789874beee50d60dcf58dd5e3908ed539fac1
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c9b4ed4edf74efe44a2f1122372b8e27ca9d9e64718dd439be96c86fb0e32ae
3
+ size 3212775159
mathmedium2-mutualposclip-0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_250/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6c701444ece8e5d8a0dbde624a063ff5b3f986da4968b0ccffa8db8889f947
3
+ size 3212775159