samyakjain commited on
Commit
d057f47
·
verified ·
1 Parent(s): 9af0f52

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 +74 -0
  2. verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/actor/huggingface/tokenizer.json +3 -0
  3. verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/actor/model_world_size_4_rank_0.pt +3 -0
  4. verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/actor/model_world_size_4_rank_1.pt +3 -0
  5. verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/actor/model_world_size_4_rank_2.pt +3 -0
  6. verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/actor/model_world_size_4_rank_3.pt +3 -0
  7. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/1.jsonl +0 -0
  8. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/130.jsonl +0 -0
  9. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/142.jsonl +0 -0
  10. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/157.jsonl +0 -0
  11. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/17.jsonl +0 -0
  12. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/20.jsonl +0 -0
  13. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/201.jsonl +0 -0
  14. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/24.jsonl +0 -0
  15. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/248.jsonl +0 -0
  16. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/268.jsonl +0 -0
  17. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/269.jsonl +0 -0
  18. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/303.jsonl +0 -0
  19. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/304.jsonl +0 -0
  20. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/307.jsonl +0 -0
  21. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/311.jsonl +0 -0
  22. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/345.jsonl +0 -0
  23. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/346.jsonl +0 -0
  24. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/375.jsonl +0 -0
  25. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/377.jsonl +3 -0
  26. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/378.jsonl +3 -0
  27. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/379.jsonl +3 -0
  28. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/38.jsonl +0 -0
  29. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/415.jsonl +0 -0
  30. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/66.jsonl +0 -0
  31. verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/89.jsonl +0 -0
  32. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/10.jsonl +3 -0
  33. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/11.jsonl +3 -0
  34. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/12.jsonl +3 -0
  35. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/13.jsonl +3 -0
  36. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/14.jsonl +3 -0
  37. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/15.jsonl +3 -0
  38. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/16.jsonl +3 -0
  39. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/17.jsonl +3 -0
  40. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/18.jsonl +3 -0
  41. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/19.jsonl +3 -0
  42. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/20.jsonl +3 -0
  43. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/23.jsonl +3 -0
  44. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/24.jsonl +3 -0
  45. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/25.jsonl +3 -0
  46. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/26.jsonl +3 -0
  47. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/27.jsonl +3 -0
  48. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/28.jsonl +3 -0
  49. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/29.jsonl +3 -0
  50. verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/30.jsonl +3 -0
.gitattributes CHANGED
@@ -33,3 +33,77 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/72.jsonl filter=lfs diff=lfs merge=lfs -text
38
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/67.jsonl filter=lfs diff=lfs merge=lfs -text
39
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/80.jsonl filter=lfs diff=lfs merge=lfs -text
40
+ verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/379.jsonl filter=lfs diff=lfs merge=lfs -text
41
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/6.jsonl filter=lfs diff=lfs merge=lfs -text
42
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/28.jsonl filter=lfs diff=lfs merge=lfs -text
43
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/25.jsonl filter=lfs diff=lfs merge=lfs -text
44
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/26.jsonl filter=lfs diff=lfs merge=lfs -text
45
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/57.jsonl filter=lfs diff=lfs merge=lfs -text
46
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/7.jsonl filter=lfs diff=lfs merge=lfs -text
47
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/32.jsonl filter=lfs diff=lfs merge=lfs -text
48
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/73.jsonl filter=lfs diff=lfs merge=lfs -text
49
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/63.jsonl filter=lfs diff=lfs merge=lfs -text
50
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/74.jsonl filter=lfs diff=lfs merge=lfs -text
51
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/62.jsonl filter=lfs diff=lfs merge=lfs -text
52
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/47.jsonl filter=lfs diff=lfs merge=lfs -text
53
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/8.jsonl filter=lfs diff=lfs merge=lfs -text
54
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/77.jsonl filter=lfs diff=lfs merge=lfs -text
55
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/24.jsonl filter=lfs diff=lfs merge=lfs -text
56
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/30.jsonl filter=lfs diff=lfs merge=lfs -text
57
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/56.jsonl filter=lfs diff=lfs merge=lfs -text
58
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/38.jsonl filter=lfs diff=lfs merge=lfs -text
59
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/9.jsonl filter=lfs diff=lfs merge=lfs -text
60
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/61.jsonl filter=lfs diff=lfs merge=lfs -text
61
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/23.jsonl filter=lfs diff=lfs merge=lfs -text
62
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/27.jsonl filter=lfs diff=lfs merge=lfs -text
63
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/41.jsonl filter=lfs diff=lfs merge=lfs -text
64
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/66.jsonl filter=lfs diff=lfs merge=lfs -text
65
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/34.jsonl filter=lfs diff=lfs merge=lfs -text
66
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/71.jsonl filter=lfs diff=lfs merge=lfs -text
67
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/39.jsonl filter=lfs diff=lfs merge=lfs -text
68
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/64.jsonl filter=lfs diff=lfs merge=lfs -text
69
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/76.jsonl filter=lfs diff=lfs merge=lfs -text
70
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/36.jsonl filter=lfs diff=lfs merge=lfs -text
71
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/42.jsonl filter=lfs diff=lfs merge=lfs -text
72
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/17.jsonl filter=lfs diff=lfs merge=lfs -text
73
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/11.jsonl filter=lfs diff=lfs merge=lfs -text
74
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/16.jsonl filter=lfs diff=lfs merge=lfs -text
75
+ verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/378.jsonl filter=lfs diff=lfs merge=lfs -text
76
+ verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/377.jsonl filter=lfs diff=lfs merge=lfs -text
77
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/69.jsonl filter=lfs diff=lfs merge=lfs -text
78
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/29.jsonl filter=lfs diff=lfs merge=lfs -text
79
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/68.jsonl filter=lfs diff=lfs merge=lfs -text
80
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/75.jsonl filter=lfs diff=lfs merge=lfs -text
81
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/48.jsonl filter=lfs diff=lfs merge=lfs -text
82
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/52.jsonl filter=lfs diff=lfs merge=lfs -text
83
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/40.jsonl filter=lfs diff=lfs merge=lfs -text
84
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/78.jsonl filter=lfs diff=lfs merge=lfs -text
85
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/50.jsonl filter=lfs diff=lfs merge=lfs -text
86
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/51.jsonl filter=lfs diff=lfs merge=lfs -text
87
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/46.jsonl filter=lfs diff=lfs merge=lfs -text
88
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/53.jsonl filter=lfs diff=lfs merge=lfs -text
89
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/79.jsonl filter=lfs diff=lfs merge=lfs -text
90
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/35.jsonl filter=lfs diff=lfs merge=lfs -text
91
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/31.jsonl filter=lfs diff=lfs merge=lfs -text
92
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/55.jsonl filter=lfs diff=lfs merge=lfs -text
93
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/54.jsonl filter=lfs diff=lfs merge=lfs -text
94
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/37.jsonl filter=lfs diff=lfs merge=lfs -text
95
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/33.jsonl filter=lfs diff=lfs merge=lfs -text
96
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/65.jsonl filter=lfs diff=lfs merge=lfs -text
97
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/70.jsonl filter=lfs diff=lfs merge=lfs -text
98
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/10.jsonl filter=lfs diff=lfs merge=lfs -text
99
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/14.jsonl filter=lfs diff=lfs merge=lfs -text
100
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/15.jsonl filter=lfs diff=lfs merge=lfs -text
101
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/12.jsonl filter=lfs diff=lfs merge=lfs -text
102
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/43.jsonl filter=lfs diff=lfs merge=lfs -text
103
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/13.jsonl filter=lfs diff=lfs merge=lfs -text
104
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/44.jsonl filter=lfs diff=lfs merge=lfs -text
105
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/18.jsonl filter=lfs diff=lfs merge=lfs -text
106
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/45.jsonl filter=lfs diff=lfs merge=lfs -text
107
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/20.jsonl filter=lfs diff=lfs merge=lfs -text
108
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/49.jsonl filter=lfs diff=lfs merge=lfs -text
109
+ verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/19.jsonl filter=lfs diff=lfs merge=lfs -text
verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/actor/huggingface/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/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:b4f90c6974a7335429b7ac95cf6cdeee89ca99ae68ffe9f6cc2729cfc5c09d86
3
+ size 7615806810
verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/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:b09bea67ec8facf9a7141c0d95902959a3dd15eb403ab5da70269de99127d09d
3
+ size 7615806810
verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/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:d5965cd0fe40a565415d12e5a662e4449e22ae7769264f15a3a3e1a15e09474e
3
+ size 7615806810
verl_math_Qwen2p5Math7B_NegRAFT_correct_rerun/global_step_400/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:a70403748262890689f7bc99cf5755a4647ffc93e0a0652c8cc549b93523edae
3
+ size 7615806810
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/130.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/142.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/157.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/17.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/20.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/201.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/24.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/248.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/268.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/269.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/303.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/304.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/307.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/311.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/345.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/346.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/375.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/377.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97bc5932bdedad46a21b8404f58e68318e956392f1e0bec05302ab797f7ff7e6
3
+ size 10599979
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/378.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d16ac56e7d667279795c3c6a1ea0519c02f30d60fc170d7341f0350ba8d23d2
3
+ size 11120014
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/379.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84d3310bc4c2bc9ee81e3510b6711c522f726880b2f971df26f1b4de8230683
3
+ size 33283979
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/38.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/415.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/66.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/89.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/10.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da570e9a5688e43c4f11256807943ff2958d52725b3b58588be6bb53d447dfb9
3
+ size 34865096
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/11.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02489e7c2ce835acad9435b654666946d9c446da66d83803ab5a867cc1ced6cd
3
+ size 11189828
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/12.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6523aac798accceb77812ec19be727b529abde8c8ede5f2f651bf546d9ba974
3
+ size 35418952
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/13.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b9c408418e6710f85f64801613d876ae2441c69e5b46f0d53ecaee08f4b953
3
+ size 35344256
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/14.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a175db05ad47fa1ae959bc2be3e0135fcfd751d614a53b918989c3abdfaef78
3
+ size 35699311
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/15.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44352be7385f4ef3c8896b36a3eaf1e5092dd77e2a8d34de8785a1acbdb800d2
3
+ size 35831018
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/16.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15435f3e0b4fc4e351055ce3ae8206e1ae941602c2f79ba302b67d5b8a0fdc2f
3
+ size 37486309
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/17.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b74256713fc9e45f07efc17cf2660635d5fa1ec24561956d9618a57bfdbbaa
3
+ size 37582535
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/18.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d99397c4a9707f6bea667b5e017e59578b1f5289fea186a00d991c281bacb17
3
+ size 40066817
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/19.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:305adce412590758160d1438c3f2b946cbbd740cefb49dc00646c37cc1a597ec
3
+ size 52888069
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/20.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c8594f4e033bc09f0f561d1376ab1f106d8eaadfa072ed7a04d7c7bf66a13e
3
+ size 48052224
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/23.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc57b3face5cb94f2dc49205e874847950018600260a7e4eb768735bf0f42271
3
+ size 30851788
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/24.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653447c9209d60abd1a54185713b10492490b989485b71331dba8337d28c2d0d
3
+ size 20866929
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/25.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24d376767ac4ce3a933ba5705a8990180b1f7297cbd859211cfb378359e15c7
3
+ size 16594236
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/26.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4855a6e3c39592424d898a1226aecc4e652fbc7f059d0801952dd4373f7456
3
+ size 17270457
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/27.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89892709f70f79ece8da2774034e8ad885af8304f63ca9dc0ac8b62cf15a563b
3
+ size 11670545
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/28.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71451d836778e3aa30c59cad4e8794a6a75425b243e76e7b688f9f9123688888
3
+ size 12923768
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/29.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a9d913fdc1ceedc1f4624076c531bb5d47d464ab4d603394b57f635a2dd286
3
+ size 16306848
verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/verl_math_Qwen2p5Math7B_NegativeLoss_32_cosine_logalso_run_tokenmean/rollouts/30.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4406473aab7c9facd04cd7848466c53b4e0c29d56aa18ad6b7bbdf9219d42abb
3
+ size 12655027