Hugging Face's logo

RL-Forgetting-Experiments-3
/
code-rl-lr-ablation

Reinforcement Learning
Safetensors
grpo
code-generation
mbpp
catastrophic-forgetting
ablation
Model card Files
xet
 Community
Evangelinejy commited on
Commit
be9aa5a
·
verified ·
1 Parent(s): 6fda9da

qwen3b_mbpp_hardcd_lam0p1_lr3e6 rollouts

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/1.jsonl +0 -0
  2. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/10.jsonl +0 -0
  3. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/100.jsonl +0 -0
  4. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/101.jsonl +0 -0
  5. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/102.jsonl +0 -0
  6. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/103.jsonl +0 -0
  7. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/104.jsonl +0 -0
  8. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/105.jsonl +0 -0
  9. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/106.jsonl +0 -0
  10. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/107.jsonl +0 -0
  11. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/108.jsonl +0 -0
  12. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/109.jsonl +0 -0
  13. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/11.jsonl +0 -0
  14. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/110.jsonl +0 -0
  15. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/111.jsonl +0 -0
  16. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/112.jsonl +0 -0
  17. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/113.jsonl +0 -0
  18. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/114.jsonl +0 -0
  19. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/115.jsonl +0 -0
  20. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/116.jsonl +0 -0
  21. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/117.jsonl +0 -0
  22. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/118.jsonl +0 -0
  23. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/119.jsonl +0 -0
  24. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/12.jsonl +0 -0
  25. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/120.jsonl +0 -0
  26. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/121.jsonl +0 -0
  27. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/122.jsonl +0 -0
  28. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/123.jsonl +0 -0
  29. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/124.jsonl +0 -0
  30. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/125.jsonl +0 -0
  31. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/126.jsonl +0 -0
  32. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/127.jsonl +0 -0
  33. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/128.jsonl +0 -0
  34. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/129.jsonl +0 -0
  35. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/13.jsonl +0 -0
  36. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/130.jsonl +0 -0
  37. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/131.jsonl +0 -0
  38. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/132.jsonl +0 -0
  39. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/133.jsonl +0 -0
  40. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/134.jsonl +0 -0
  41. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/135.jsonl +0 -0
  42. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/136.jsonl +0 -0
  43. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/137.jsonl +0 -0
  44. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/138.jsonl +0 -0
  45. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/139.jsonl +0 -0
  46. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/14.jsonl +0 -0
  47. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/140.jsonl +0 -0
  48. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/141.jsonl +0 -0
  49. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/142.jsonl +0 -0
  50. qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/143.jsonl +0 -0
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/10.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/100.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/101.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/102.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/103.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/104.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/105.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/106.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/107.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/108.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/109.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/11.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/110.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/111.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/112.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/113.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/114.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/115.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/116.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/117.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/118.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/119.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/12.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/120.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/121.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/122.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/123.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/124.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/125.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/126.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/127.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/128.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/129.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/13.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/130.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/131.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/132.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/133.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/134.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/135.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/136.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/137.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/138.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/139.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/14.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/140.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/141.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/142.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
qwen3b_mbpp_hardcd_lam0p1_lr3e6/rollouts/training/143.jsonl ADDED
The diff for this file is too large to render. See raw diff