Hugging Face's logo

jonathanjordan21
/
my-thesis

Model card Files
xet
 Community
jonathanjordan21 commited on
Commit
1ff422e
·
verified ·
1 Parent(s): 2ed511c

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. outputs/assets/dpo/train|epoch.png +0 -0
  2. outputs/assets/dpo/train|grad_norm.png +0 -0
  3. outputs/assets/dpo/train|learning_rate.png +0 -0
  4. outputs/assets/dpo/train|logits|chosen.png +0 -0
  5. outputs/assets/dpo/train|logits|rejected.png +0 -0
  6. outputs/assets/dpo/train|logps|chosen.png +0 -0
  7. outputs/assets/dpo/train|logps|rejected.png +0 -0
  8. outputs/assets/dpo/train|loss.png +0 -0
  9. outputs/assets/dpo/train|nll_loss.png +0 -0
  10. outputs/assets/dpo/train|rewards|accuracies.png +0 -0
  11. outputs/assets/dpo/train|rewards|chosen.png +0 -0
  12. outputs/assets/dpo/train|rewards|margins.png +0 -0
  13. outputs/assets/dpo/train|rewards|rejected.png +0 -0
  14. outputs/assets/dpo/train|total_flos.png +0 -0
  15. outputs/assets/dpo/train|train_loss.png +0 -0
  16. outputs/assets/dpo/train|train_runtime.png +0 -0
  17. outputs/assets/dpo/train|train_samples_per_second.png +0 -0
  18. outputs/assets/dpo/train|train_steps_per_second.png +0 -0
  19. outputs/assets/sft/train|epoch.png +0 -0
  20. outputs/assets/sft/train|grad_norm.png +0 -0
  21. outputs/assets/sft/train|learning_rate.png +0 -0
  22. outputs/assets/sft/train|loss.png +0 -0
  23. outputs/assets/sft/train|total_flos.png +0 -0
  24. outputs/assets/sft/train|train_loss.png +0 -0
  25. outputs/assets/sft/train|train_runtime.png +0 -0
  26. outputs/assets/sft/train|train_samples_per_second.png +0 -0
  27. outputs/assets/sft/train|train_steps_per_second.png +0 -0
  28. outputs/assets/st/train|epoch.png +0 -0
  29. outputs/assets/st/train|grad_norm.png +0 -0
  30. outputs/assets/st/train|learning_rate.png +0 -0
  31. outputs/assets/st/train|loss.png +0 -0
  32. outputs/assets/st/train|total_flos.png +0 -0
  33. outputs/assets/st/train|train_loss.png +0 -0
  34. outputs/assets/st/train|train_runtime.png +0 -0
  35. outputs/assets/st/train|train_samples_per_second.png +0 -0
  36. outputs/assets/st/train|train_steps_per_second.png +0 -0
outputs/assets/dpo/train|epoch.png ADDED
outputs/assets/dpo/train|grad_norm.png ADDED
outputs/assets/dpo/train|learning_rate.png ADDED
outputs/assets/dpo/train|logits|chosen.png ADDED
outputs/assets/dpo/train|logits|rejected.png ADDED
outputs/assets/dpo/train|logps|chosen.png ADDED
outputs/assets/dpo/train|logps|rejected.png ADDED
outputs/assets/dpo/train|loss.png ADDED
outputs/assets/dpo/train|nll_loss.png ADDED
outputs/assets/dpo/train|rewards|accuracies.png ADDED
outputs/assets/dpo/train|rewards|chosen.png ADDED
outputs/assets/dpo/train|rewards|margins.png ADDED
outputs/assets/dpo/train|rewards|rejected.png ADDED
outputs/assets/dpo/train|total_flos.png ADDED
outputs/assets/dpo/train|train_loss.png CHANGED
outputs/assets/dpo/train|train_runtime.png ADDED
outputs/assets/dpo/train|train_samples_per_second.png ADDED
outputs/assets/dpo/train|train_steps_per_second.png ADDED
outputs/assets/sft/train|epoch.png ADDED
outputs/assets/sft/train|grad_norm.png ADDED
outputs/assets/sft/train|learning_rate.png ADDED
outputs/assets/sft/train|loss.png ADDED
outputs/assets/sft/train|total_flos.png ADDED
outputs/assets/sft/train|train_loss.png CHANGED
outputs/assets/sft/train|train_runtime.png ADDED
outputs/assets/sft/train|train_samples_per_second.png ADDED
outputs/assets/sft/train|train_steps_per_second.png ADDED
outputs/assets/st/train|epoch.png ADDED
outputs/assets/st/train|grad_norm.png ADDED
outputs/assets/st/train|learning_rate.png ADDED
outputs/assets/st/train|loss.png ADDED
outputs/assets/st/train|total_flos.png ADDED
outputs/assets/st/train|train_loss.png CHANGED
outputs/assets/st/train|train_runtime.png ADDED
outputs/assets/st/train|train_samples_per_second.png ADDED
outputs/assets/st/train|train_steps_per_second.png ADDED