Hugging Face's logo

samyakjain
/
MSRBackupsReasoningCheckpoints

Model card Files
xet
Community
samyakjain commited on
Commit
059a7b8
·
verified ·
1 Parent(s): d057f47

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. verl_math_Qwen2p5Math7B_NegLoss_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/400.jsonl +0 -0
  2. verl_math_Qwen2p5Math7B_NegLoss_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/431.jsonl +0 -0
  3. verl_math_Qwen2p5Math7B_NegRAFT_ZeroAdv_onpolicy_numina_hard_rerun/rollouts/146.jsonl +0 -0
  4. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/1.jsonl +0 -0
  5. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/101.jsonl +0 -0
  6. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/102.jsonl +0 -0
  7. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/103.jsonl +0 -0
  8. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/104.jsonl +0 -0
  9. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/107.jsonl +0 -0
  10. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/11.jsonl +0 -0
  11. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/110.jsonl +0 -0
  12. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/116.jsonl +0 -0
  13. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/12.jsonl +0 -0
  14. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/15.jsonl +0 -0
  15. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/2.jsonl +0 -0
  16. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/20.jsonl +0 -0
  17. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/27.jsonl +0 -0
  18. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/28.jsonl +0 -0
  19. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/29.jsonl +0 -0
  20. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/32.jsonl +0 -0
  21. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/33.jsonl +0 -0
  22. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/35.jsonl +0 -0
  23. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/36.jsonl +0 -0
  24. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/40.jsonl +0 -0
  25. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/43.jsonl +0 -0
  26. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/44.jsonl +0 -0
  27. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/45.jsonl +0 -0
  28. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/51.jsonl +0 -0
  29. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/54.jsonl +0 -0
  30. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/55.jsonl +0 -0
  31. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/56.jsonl +0 -0
  32. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/59.jsonl +0 -0
  33. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/60.jsonl +0 -0
  34. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/61.jsonl +0 -0
  35. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/65.jsonl +0 -0
  36. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/66.jsonl +0 -0
  37. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/67.jsonl +0 -0
  38. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/68.jsonl +0 -0
  39. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/69.jsonl +0 -0
  40. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/71.jsonl +0 -0
  41. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/72.jsonl +0 -0
  42. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/75.jsonl +0 -0
  43. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/82.jsonl +0 -0
  44. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/83.jsonl +0 -0
  45. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/84.jsonl +0 -0
  46. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/85.jsonl +0 -0
  47. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/87.jsonl +0 -0
  48. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/89.jsonl +0 -0
  49. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/9.jsonl +0 -0
  50. verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/97.jsonl +0 -0
verl_math_Qwen2p5Math7B_NegLoss_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/400.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegLoss_onpolicy_numina_hard_rerun_DRGRPO_norm/rollouts/431.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_NegRAFT_ZeroAdv_onpolicy_numina_hard_rerun/rollouts/146.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/101.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/102.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/103.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/104.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/107.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/11.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/110.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/116.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/12.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/15.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/2.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/20.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/27.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/28.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/29.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/32.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/33.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/35.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/36.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/40.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/43.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/44.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/45.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/51.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/54.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/55.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/56.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/59.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/60.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/61.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/65.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/66.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/67.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/68.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/69.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/71.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/72.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/75.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/82.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/83.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/84.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/85.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/87.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/89.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/9.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
verl_math_Qwen2p5Math7B_RAFT_online_cosine_logalso_run_tokenmean_Adv0/rollouts/97.jsonl ADDED
The diff for this file is too large to render. See raw diff