kangdawei commited on
Commit
576de5e
·
verified ·
1 Parent(s): 4c41482

Training in progress, step 500

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. reward_data/all_rewards.csv +2 -2
  3. reward_plots/advantage_plot_step_250.png +0 -0
  4. reward_plots/advantage_plot_step_260.png +0 -0
  5. reward_plots/advantage_plot_step_270.png +0 -0
  6. reward_plots/advantage_plot_step_280.png +0 -0
  7. reward_plots/advantage_plot_step_290.png +0 -0
  8. reward_plots/advantage_plot_step_300.png +0 -0
  9. reward_plots/advantage_plot_step_310.png +0 -0
  10. reward_plots/advantage_plot_step_320.png +0 -0
  11. reward_plots/advantage_plot_step_330.png +0 -0
  12. reward_plots/advantage_plot_step_340.png +0 -0
  13. reward_plots/advantage_plot_step_350.png +0 -0
  14. reward_plots/advantage_plot_step_360.png +0 -0
  15. reward_plots/advantage_plot_step_370.png +0 -0
  16. reward_plots/advantage_plot_step_380.png +0 -0
  17. reward_plots/advantage_plot_step_390.png +0 -0
  18. reward_plots/advantage_plot_step_400.png +0 -0
  19. reward_plots/advantage_plot_step_410.png +0 -0
  20. reward_plots/advantage_plot_step_420.png +0 -0
  21. reward_plots/advantage_plot_step_430.png +0 -0
  22. reward_plots/advantage_plot_step_440.png +0 -0
  23. reward_plots/advantage_plot_step_450.png +0 -0
  24. reward_plots/advantage_plot_step_460.png +0 -0
  25. reward_plots/advantage_plot_step_470.png +0 -0
  26. reward_plots/advantage_plot_step_480.png +0 -0
  27. reward_plots/advantage_plot_step_490.png +0 -0
  28. reward_plots/reward_comparison_step_250.png +0 -0
  29. reward_plots/reward_comparison_step_260.png +0 -0
  30. reward_plots/reward_comparison_step_270.png +0 -0
  31. reward_plots/reward_comparison_step_280.png +0 -0
  32. reward_plots/reward_comparison_step_290.png +0 -0
  33. reward_plots/reward_comparison_step_300.png +0 -0
  34. reward_plots/reward_comparison_step_310.png +0 -0
  35. reward_plots/reward_comparison_step_320.png +0 -0
  36. reward_plots/reward_comparison_step_330.png +0 -0
  37. reward_plots/reward_comparison_step_340.png +0 -0
  38. reward_plots/reward_comparison_step_350.png +0 -0
  39. reward_plots/reward_comparison_step_360.png +0 -0
  40. reward_plots/reward_comparison_step_370.png +0 -0
  41. reward_plots/reward_comparison_step_380.png +0 -0
  42. reward_plots/reward_comparison_step_390.png +0 -0
  43. reward_plots/reward_comparison_step_400.png +0 -0
  44. reward_plots/reward_comparison_step_410.png +0 -0
  45. reward_plots/reward_comparison_step_420.png +0 -0
  46. reward_plots/reward_comparison_step_430.png +0 -0
  47. reward_plots/reward_comparison_step_440.png +0 -0
  48. reward_plots/reward_comparison_step_450.png +0 -0
  49. reward_plots/reward_comparison_step_460.png +0 -0
  50. reward_plots/reward_comparison_step_470.png +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:526abd51fabadb3de567d0815ed209d5fa39e63259b23259d890655210d93882
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c0c21b3fde6eae3f5b0efab95e70962e03a706b8b735830938126492a75a97
3
  size 3554214752
reward_data/all_rewards.csv CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43c4b9eba74a847869fcf0cecbd263bb7249a038a139abb0e0a73e8c6d1251a0
3
- size 165166389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7975414281b33335edf63f902814e9f8652d26def3823295373a47439f917c43
3
+ size 180446461
reward_plots/advantage_plot_step_250.png ADDED
reward_plots/advantage_plot_step_260.png ADDED
reward_plots/advantage_plot_step_270.png ADDED
reward_plots/advantage_plot_step_280.png ADDED
reward_plots/advantage_plot_step_290.png ADDED
reward_plots/advantage_plot_step_300.png ADDED
reward_plots/advantage_plot_step_310.png ADDED
reward_plots/advantage_plot_step_320.png ADDED
reward_plots/advantage_plot_step_330.png ADDED
reward_plots/advantage_plot_step_340.png ADDED
reward_plots/advantage_plot_step_350.png ADDED
reward_plots/advantage_plot_step_360.png ADDED
reward_plots/advantage_plot_step_370.png ADDED
reward_plots/advantage_plot_step_380.png ADDED
reward_plots/advantage_plot_step_390.png ADDED
reward_plots/advantage_plot_step_400.png ADDED
reward_plots/advantage_plot_step_410.png ADDED
reward_plots/advantage_plot_step_420.png ADDED
reward_plots/advantage_plot_step_430.png ADDED
reward_plots/advantage_plot_step_440.png ADDED
reward_plots/advantage_plot_step_450.png ADDED
reward_plots/advantage_plot_step_460.png ADDED
reward_plots/advantage_plot_step_470.png ADDED
reward_plots/advantage_plot_step_480.png ADDED
reward_plots/advantage_plot_step_490.png ADDED
reward_plots/reward_comparison_step_250.png ADDED
reward_plots/reward_comparison_step_260.png ADDED
reward_plots/reward_comparison_step_270.png ADDED
reward_plots/reward_comparison_step_280.png ADDED
reward_plots/reward_comparison_step_290.png ADDED
reward_plots/reward_comparison_step_300.png ADDED
reward_plots/reward_comparison_step_310.png ADDED
reward_plots/reward_comparison_step_320.png ADDED
reward_plots/reward_comparison_step_330.png ADDED
reward_plots/reward_comparison_step_340.png ADDED
reward_plots/reward_comparison_step_350.png ADDED
reward_plots/reward_comparison_step_360.png ADDED
reward_plots/reward_comparison_step_370.png ADDED
reward_plots/reward_comparison_step_380.png ADDED
reward_plots/reward_comparison_step_390.png ADDED
reward_plots/reward_comparison_step_400.png ADDED
reward_plots/reward_comparison_step_410.png ADDED
reward_plots/reward_comparison_step_420.png ADDED
reward_plots/reward_comparison_step_430.png ADDED
reward_plots/reward_comparison_step_440.png ADDED
reward_plots/reward_comparison_step_450.png ADDED
reward_plots/reward_comparison_step_460.png ADDED
reward_plots/reward_comparison_step_470.png ADDED