Views
No views yet
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0005 | 0.2667 | 50 | 0.0003 | 0.8841 | -7.2237 | 1.0 | 8.1078 | -111.6638 | -13.8759 | -1.0293 | -0.9511 |
| 0.0 | 0.5333 | 100 | 0.0000 | 0.9749 | -9.2781 | 1.0 | 10.2530 | -132.2077 | -12.9677 | -1.0433 | -0.9670 |
| 0.0 | 0.8 | 150 | 0.0000 | 1.0216 | -10.1753 | 1.0 | 11.1969 | -141.1800 | -12.5008 | -1.0507 | -0.9741 |
| 0.0 | 1.0667 | 200 | 0.0000 | 1.0446 | -10.7078 | 1.0 | 11.7524 | -146.5044 | -12.2703 | -1.0543 | -0.9770 |
| 0.0 | 1.3333 | 250 | 0.0000 | 1.0661 | -11.1000 | 1.0 | 12.1660 | -150.4264 | -12.0562 | -1.0548 | -0.9771 |
| 0.0 | 1.6 | 300 | 0.0000 | 1.0681 | -11.3752 | 1.0 | 12.4433 | -153.1791 | -12.0359 | -1.0551 | -0.9769 |
| 0.0 | 1.8667 | 350 | 0.0000 | 1.0705 | -11.5935 | 1.0 | 12.6640 | -155.3615 | -12.0115 | -1.0569 | -0.9780 |
| 0.0 | 2.1333 | 400 | 0.0000 | 1.0655 | -11.7889 | 1.0 | 12.8544 | -157.3161 | -12.0617 | -1.0580 | -0.9789 |
| 0.0 | 2.4 | 450 | 0.0000 | 1.0692 | -11.9273 | 1.0 | 12.9966 | -158.7003 | -12.0244 | -1.0574 | -0.9775 |
| 0.0 | 2.6667 | 500 | 0.0000 | 1.0713 | -12.0402 | 1.0 | 13.1116 | -159.8291 | -12.0034 | -1.0592 | -0.9789 |
| 0.0 | 2.9333 | 550 | 0.0000 | 1.0676 | -12.1498 | 1.0 | 13.2174 | -160.9253 | -12.0412 | -1.0594 | -0.9787 |
| 0.0 | 3.2 | 600 | 0.0000 | 1.0715 | -12.2198 | 1.0 | 13.2913 | -161.6252 | -12.0021 | -1.0585 | -0.9777 |
| 0.0 | 3.4667 | 650 | 0.0000 | 1.0686 | -12.2724 | 1.0 | 13.3410 | -162.1508 | -12.0304 | -1.0601 | -0.9788 |
| 0.0 | 3.7333 | 700 | 0.0000 | 1.0703 | -12.3000 | 1.0 | 13.3703 | -162.4264 | -12.0133 | -1.0601 | -0.9787 |
| 0.0 | 4.0 | 750 | 0.0000 | 1.0660 | -12.3243 | 1.0 | 13.3902 | -162.6695 | -12.0572 | -1.0605 | -0.9791 |
| 0.0 | 4.2667 | 800 | 0.0000 | 1.0652 | -12.3416 | 1.0 | 13.4068 | -162.8429 | -12.0648 | -1.0601 | -0.9785 |
| 0.0 | 4.5333 | 850 | 0.0000 | 1.0688 | -12.3369 | 1.0 | 13.4057 | -162.7962 | -12.0292 | -1.0594 | -0.9780 |
| 0.0 | 4.8 | 900 | 0.0000 | 1.0658 | -12.3415 | 1.0 | 13.4073 | -162.8423 | -12.0590 | -1.0597 | -0.9784 |
| 0.0 | 5.0667 | 950 | 0.0000 | 1.0678 | -12.3446 | 1.0 | 13.4123 | -162.8726 | -12.0391 | -1.0600 | -0.9785 |
| 0.0 | 5.3333 | 1000 | 0.0000 | 1.0682 | -12.3428 | 1.0 | 13.4110 | -162.8549 | -12.0348 | -1.0599 | -0.9785 |