tyzhu commited on
Commit
a0d07fa
·
verified ·
1 Parent(s): 875f494

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 +3 -0
  2. mathmedium2-grpo-qwen3-1.7b-4k-step-50/model.safetensors +3 -0
  3. mathmedium2-grpo-qwen3-1.7b-4k-step-50/tokenizer.json +3 -0
  4. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/extra_state_world_size_8_rank_0.pt +3 -0
  5. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/extra_state_world_size_8_rank_1.pt +3 -0
  6. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/extra_state_world_size_8_rank_3.pt +3 -0
  7. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/extra_state_world_size_8_rank_4.pt +3 -0
  8. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/model_world_size_8_rank_1.pt +3 -0
  11. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/model_world_size_8_rank_2.pt +3 -0
  12. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/model_world_size_8_rank_3.pt +3 -0
  13. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/model_world_size_8_rank_4.pt +3 -0
  14. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/model_world_size_8_rank_5.pt +3 -0
  15. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/model_world_size_8_rank_6.pt +3 -0
  16. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/actor/model_world_size_8_rank_7.pt +3 -0
  17. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/data.pt +3 -0
  18. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/extra_state_world_size_8_rank_0.pt +3 -0
  19. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/extra_state_world_size_8_rank_1.pt +3 -0
  20. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/extra_state_world_size_8_rank_2.pt +3 -0
  21. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/extra_state_world_size_8_rank_3.pt +3 -0
  22. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/extra_state_world_size_8_rank_4.pt +3 -0
  23. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/extra_state_world_size_8_rank_5.pt +3 -0
  24. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/extra_state_world_size_8_rank_6.pt +3 -0
  25. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/extra_state_world_size_8_rank_7.pt +3 -0
  26. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/huggingface/model-00001-of-00003.safetensors +3 -0
  27. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/huggingface/model-00002-of-00003.safetensors +3 -0
  28. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/huggingface/model-00003-of-00003.safetensors +3 -0
  29. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/huggingface/tokenizer.json +3 -0
  30. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_0.pt +3 -0
  31. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_1.pt +3 -0
  32. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_2.pt +3 -0
  33. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_3.pt +3 -0
  34. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_4.pt +3 -0
  35. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_5.pt +3 -0
  36. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_6.pt +3 -0
  37. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_7.pt +3 -0
  38. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_0.pt +3 -0
  39. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_1.pt +3 -0
  40. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_2.pt +3 -0
  41. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_3.pt +3 -0
  42. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_4.pt +3 -0
  43. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_5.pt +3 -0
  44. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_6.pt +3 -0
  45. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_7.pt +3 -0
  46. mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/data.pt +3 -0
  47. pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00001-of-00003.safetensors +3 -0
  48. pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00002-of-00003.safetensors +3 -0
  49. pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00003-of-00003.safetensors +3 -0
  50. pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -80,3 +80,6 @@ mathhard2-grpo-qwen3-1.7b-4k-step-150/tokenizer.json filter=lfs diff=lfs merge=l
80
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
82
  pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/critic/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
80
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
  mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.8/global_step_200/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
82
  pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/critic/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
83
+ pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
84
+ mathmedium2-grpo-qwen3-1.7b-4k-step-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
85
+ mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mathmedium2-grpo-qwen3-1.7b-4k-step-50/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713c554e6c5bc3edfb4b8f082854c885c7c8c9352801d62a44482163f4905154
3
+ size 4063515640
mathmedium2-grpo-qwen3-1.7b-4k-step-50/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:2eb7cd6b302d2525cd28bb6928a8c37e3a13054ef8ac2756d00ea2f21c5bd751
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:7698c8a7b8ab8f76ac31d12d53254a756e879d9d385a1234f15c8c834ad07a94
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:4bc3d9ff6dba79111c00943276ec92b15c40b24d88617eaf2595bd8335a68e3b
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:0d38df6bd2f7443d79dd6d6510eca3d68e8392bf1a7bbb2f68c13dc01d1cde1b
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:4fb535362accaf82d9e967f5232e06e262c85023c749e0849f7dad0a2d119d17
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:eba224a92f943c0439929f871574f511b329b72277d4e4ff301d4c6152f45c17
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:da024c873ad4f8b3bd8111fa965b21f12151a7d762b64698342b762ab5a08707
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:1e40d5015559cebfe6fbad585e05c78c87d0e27577c4494331f04312380d8b1e
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:1ba25809be24d437f67765cfdc12d3d404f6e8acf977fa82e3fddd0f12671ce7
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:091f102e034d5861ebd4fe6ec80f3d4fcdb7b77307231c497d11534650235156
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:1204eef35dff081cf2716e19cbb8bd49fbf030e14b3f8cb56211989a417870f9
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:be216ff401337e99eb27bcba34e9fa1544e1262d976568727c92ccf475b10a7b
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:f264aaa80c8277730ce228956a3f97d8f20843f5b4744743bb97ca659c1d2099
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_250/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3114cdd46b6fc9be44685a517aed2c2062d5df73f86219b1c34e7a661003c007
3
+ size 1492
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/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 sha256:1493eada9c6a6d3368b105b2aa52d5146386b36b766b82ddac25bc5ea5aee411
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/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:e8db444d243c8a182f5343303b25d1695efa60c81a8d95352786622a33e6fb3b
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:53161131d5f906a04a818e78a8f132617a7004a9796ed720024146f13ba9cc1b
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/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 sha256:1a8312bf146d0b22a03f66c9ea564afe7a53b799e6c0be644719063794a86eaa
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/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 sha256:665d16ed4ee5ab20c657b14cea8f1711797c6c58e851ea09639a4e71a020a788
3
+ size 14696
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:55ff68550a80e7aa6cdf8a20cc95717e940831bc5347c3d944909db841c84516
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/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 sha256:87257a0621886cb1d85a2777c39cb33f3106b9f0526d2014e964ce7ae0db7501
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/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 sha256:5f13b6ba4887a5ba54f0e05f7e88b68e5162df83a893e62362f76236c6e8e44b
3
+ size 14632
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:a1b484396943538c31215f572618960448abb526cc16e1311fc00fd0810d1fe5
3
+ size 4998767360
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:507c65099108549052ab8b6fe3e55cc7b4dd7350cee13d94875498d615b6de9b
3
+ size 4932808968
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:46f928128a5c3b66af2352d0b51cdb9cd13c85fe6566099c804a4d07630a2a1d
3
+ size 4495462048
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:cb73051641636547e4d67639816ac809a85ebda33aca683385737566b04ada87
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ce5f652f2aa723f4605636c39fb398de898f63e1b41b53e8bfec1e7f943bf1
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004152e7d0225ded30fc2a39ec7fb35f4ad2e2be697ff598b38d3652ca431b23
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2086aa464c7f322549fef675026cc1679f3a676a1f7384279300467ab5b53c21
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ffeee6fb064f276719b235fd9e30e01996149f9437f88af8daaa9e55abf7494
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9913b3928aefeb4f8227cbb362ca7eb5d316ff5fead2da2d1a30fffcb2711ac6
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:960871b49d58d1966fe3d4fec8c709d9066cefda46de523a15910861e85e26a2
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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:c047d8298bc4859eb995d54ad9a264c4d95b12ce8c6f3f1de28246fa47252940
3
+ size 1803528186
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/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 sha256:57b7d5d81e48be42c5966c68d441618755b82e1600263f4f18a4f5f2e44d1d15
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ccae06d658a2bb756087e6bc64c4cd51844d1f60613306d6154bb0fd79d4bb8
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f0f7c4c8908b8a7ad0806da1a13f0056b3956b90c8de7263bed040846b0ce22
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ab62d14e69e6799c46587fe12cdf563994e4488050e88a60b220b1d50956ba
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eda1cdce3ba9c2a8ea17bb0a6af26b04e80d24ae12d0545834f94ea32fe4054
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58db08c222886da6daa6f8d126425c57cbc760933a9a4e3019605157e4c67e1e
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/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:e99974036eb8b3a2c12bc9841beb1a74ff8e1970e8e696c1b10d93dbbfeccc80
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e74a05c4c6c06a1f3b9d901aeb5217b18e87320a5d1f65745fd89c9ffd887cf
3
+ size 3212775159
mathmedium2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt_delete-0.2/global_step_300/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce61bb8aed026137887ea2c74f4d19eb8da2c3413c2230ebd2fdee86d87be612
3
+ size 1492
pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3402b56a12a19767bf9f117afab4466f370a207a3363aa18d734bc2cdde5cf3e
3
+ size 4998767360
pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ede8b030da48de34ed482c41e5a8a011b2d0ff3cd294cfee04cd6be70660cee
3
+ size 4932808968
pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262f62d7acedbcfb6ed290f2bca09462b8f5ccd8ba9959c9d53aeadc4d8e7bdb
3
+ size 4495462048
pilecc_cont2-r1-ppo-llama3.2-3b-em-warmup-0.05-rouge-rouge5-temperature-1.0/actor/global_step_300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920