tyzhu commited on
Commit
da15303
·
verified ·
1 Parent(s): 4d43abd

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 +2 -0
  2. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_0.pt +3 -0
  3. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_1.pt +3 -0
  4. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_2.pt +3 -0
  5. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_3.pt +3 -0
  6. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_4.pt +3 -0
  7. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_5.pt +3 -0
  8. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  11. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  12. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_0.pt +3 -0
  13. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_1.pt +3 -0
  14. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_2.pt +3 -0
  15. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_3.pt +3 -0
  16. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_4.pt +3 -0
  17. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_5.pt +3 -0
  18. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_6.pt +3 -0
  19. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/model_world_size_8_rank_7.pt +3 -0
  20. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/data.pt +3 -0
  21. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_0.pt +3 -0
  22. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_1.pt +3 -0
  23. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_2.pt +3 -0
  24. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_3.pt +3 -0
  25. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_4.pt +3 -0
  26. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_5.pt +3 -0
  27. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_6.pt +3 -0
  28. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/extra_state_world_size_8_rank_7.pt +3 -0
  29. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  30. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  31. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  32. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/tokenizer.json +3 -0
  33. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_0.pt +3 -0
  34. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_1.pt +3 -0
  35. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_2.pt +3 -0
  36. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_3.pt +3 -0
  37. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_4.pt +3 -0
  38. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_5.pt +3 -0
  39. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_6.pt +3 -0
  40. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/model_world_size_8_rank_7.pt +3 -0
  41. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/data.pt +3 -0
  42. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_2.pt +3 -0
  43. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/extra_state_world_size_8_rank_5.pt +3 -0
  44. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  45. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  46. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  47. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/tokenizer.json +3 -0
  48. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_0.pt +3 -0
  49. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/model_world_size_8_rank_7.pt +3 -0
  50. mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/optim_world_size_8_rank_0.pt +3 -0
.gitattributes CHANGED
@@ -58,3 +58,5 @@ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step
58
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
  mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
58
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.2/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
  mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
+ mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
+ mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:d5378f9d1318713d6ff5e1b27fdabef97ec2866075ebde45c0708e9bf22f9258
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:9b3e34aba21a60161a0023a6face27c217ab654af373c11f0f3a3a875c04cc47
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:df4ac53f06c84b6549714e9aba8f1049136965c8f1abae685b5beae1785fed33
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:f8a8ad62eed68b8c8aac953981108334620a882e78f8b551dd354d2a5b1b87e8
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:28c3a6907e8422067af25e6a381fafe4438323af7a42236e666ba00892551f3f
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:54299ecc2d7f0d0f04755879441cbd2b0e1077c856409c69df04a062ef53585c
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:6cb155dde2735638859c1c3edec47d85d1a69898be2dbdea5e80e9644434c2b1
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:ee682c14324ced329eff7f7a8f86ccb64fb8b9c6df1f1b3aff55c710819abcce
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dc85b2545b6e995b6bbf25ba57b80330f8607fc1e8beb7fd4f96de11b7b5be7
3
+ size 4998767360
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:968afeeaa9e0954f49566dae1848f2185e34e296b881577c6245b0c60f46e94f
3
+ size 4932808968
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:573b163c34e52b7f7c5ca8da71980b4ae5c219bcf65338e4f4c0996a3d578ddf
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:cb47755a2efe9dd12cbb20ca273ae8705085a576ab559a7028c0ff0b179720da
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:35616258c34969da15201af13896774feaee27660100c1fe3b0966326cf0f6a9
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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:a01ca7826afd9137b7cbc2bb94e0db0637ce2eb5ba74c5f2013c9a53036c8f35
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:55393d72be9bf6c2c51a8c5a82727438bbf599611a1edf098ed4f837239b8755
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:70f60a2b0c999d95592d6627176b2f3bd072f5f969b042786d16512242d859da
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:657e084dc4028ef70571d5d9c6c5929f23996872e90da1b4f3a7ed23bd614462
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/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 sha256:8b53847166cf4b9a8d6c6cb69c00b5d194a06d45e1266ee1d43359fbf6dacc07
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70942094b5268cf0012483adc1c8f3240f18e59ab27f28f282cd079aa097e8a
3
+ size 1492
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:4aa1a0c801d1f6266c59a1398d561a1974abd45eca893f34b4114961659c1d3d
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:9268168cb5eb4d49fe2a36858c23559ab105696ab1337e13f176af396fd6de18
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:90f5757a2a940c9dbada2b08cc23bd81d354e9b77dc8c65fb300f716f18878fb
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:85c0714d9e8af0301dc19de33eb16daa7de4586a5a422162c5e669fa9b24b050
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:4ded6dca4c903b6d5ca53e3e3812a18ed7b134f61b16e308f8a5e9f1f85ba8e3
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:829f331fd554564792cf50927da503707386a33a3dd30b319333cfc240c9fd97
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:f804eaba51f71a0ee7daf278e75160162a499becbb16199cdee7f02ae476b66a
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:203559c991d67dfd541b63d1b59460b0081ce229b2318038c07ae1fb579ace9e
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c267fc34d44f10cdf03b82e50a48b301fe81d38457b49c8c4f7bd18adde74907
3
+ size 4998767360
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1eff99135d7c50f5c9e7aea46b827484496bff6908e95c8d791c026e54ea634
3
+ size 4932808968
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c45aabe332a834869b7317805de045b0e6cd3442529cebb6bff7748a7fbec4
3
+ size 4495462048
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/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:e566f0301d51de2e1fcaab31934c0cc1b132143ff5695c2c9b7594de40bda7fb
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:c8e563ba122253ca1b3fbc3a9399e65beea80db6779432e27ae6a7c7286b1317
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:454acf28b6a0b1b1112dcf6fdc1262c4face52a2b090a63f7bf2bc378de30ba4
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:4cfe13499563ece2e96edaa1230c59dbe6159459dbca1b447648a335291fbfbb
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:7b8cdb709097f3aba4f8f91c2bc9788dbfe20b0c613d0f594e14b3f688a524ea
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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:f2c285f5b84db3e13e4e54e211594b43b714a825f690954e6c8d880c90025f4a
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:43ea97645925f72cc0cdcb90a4b32e240e0e39a8ea354f02b4b056aec631ef59
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-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 sha256:3dd50a321157e8bec4e8367999b4871119e9589f87f2b79a14b047efef2d7007
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_250/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f7b5ea5c3e11506d33811ca95001f5f2e24ab491cd6697d5054e96a90cf4cb
3
+ size 1492
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/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:bf20e63362aa747876f85149101ecbbcb05a58a763c999ecacb1c2001e2d7661
3
+ size 14632
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/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 sha256:816e2078b526fb5b5ed1f35eeb97d729b8ca41670adcca568e80ed1861c943ba
3
+ size 14696
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfa35df7eedb9d0e4d7dee8d726ceac7db4b65fc719ad0f3992b951632193b7
3
+ size 4998767360
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3d3ec0d7e48d5f07c5ddcdd3b7709bddd553a9318c07022084b5eaa498d439
3
+ size 4932808968
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959cf6521363497e9a2bf49114ebee92e83342d8d9197ca67a7e36f9c0ce248e
3
+ size 4495462048
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/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:c9fc93bd26aa971f0096465a935ed2cfa5e0cb5e62a39ea438e2171843ce77af
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/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:d64c42d3e332f54167f0944c593d10508f6fae0ccab4a6bffc7c4134afc36911
3
+ size 1803528186
mathmedium2-mutualposclip0.2-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_300/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:f81d527372dce7097f6f19060bff57c2040bc32deb5c518c615681a808c14b15
3
+ size 3212775159