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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0 | 0.2667 | 50 | 0.0000 | 0.5713 | -13.1036 | 1.0 | 13.6749 | -114.5601 | -34.8228 | -2.1916 | -2.2124 |
| 0.0 | 0.5333 | 100 | 0.0000 | 0.4941 | -14.7667 | 1.0 | 15.2608 | -120.1038 | -35.0802 | -2.1804 | -2.2049 |
| 0.0 | 0.8 | 150 | 0.0000 | 0.4984 | -15.3187 | 1.0 | 15.8171 | -121.9437 | -35.0656 | -2.1770 | -2.2034 |
| 0.0 | 1.0667 | 200 | 0.0000 | 0.4877 | -15.6734 | 1.0 | 16.1611 | -123.1262 | -35.1015 | -2.1731 | -2.2001 |
| 0.0 | 1.3333 | 250 | 0.0000 | 0.4731 | -15.9681 | 1.0 | 16.4411 | -124.1084 | -35.1502 | -2.1713 | -2.1995 |
| 0.0 | 1.6 | 300 | 0.0000 | 0.4585 | -16.1886 | 1.0 | 16.6471 | -124.8435 | -35.1987 | -2.1685 | -2.1973 |
| 0.0 | 1.8667 | 350 | 0.0000 | 0.4539 | -16.3717 | 1.0 | 16.8257 | -125.4539 | -35.2140 | -2.1666 | -2.1960 |
| 0.0 | 2.1333 | 400 | 0.0000 | 0.4523 | -16.5548 | 1.0 | 17.0072 | -126.0642 | -35.2192 | -2.1645 | -2.1945 |
| 0.0 | 2.4 | 450 | 0.0000 | 0.4426 | -16.6528 | 1.0 | 17.0953 | -126.3907 | -35.2518 | -2.1633 | -2.1933 |
| 0.0 | 2.6667 | 500 | 0.0000 | 0.4351 | -16.7438 | 1.0 | 17.1789 | -126.6941 | -35.2766 | -2.1622 | -2.1926 |
| 0.0 | 2.9333 | 550 | 0.0000 | 0.4274 | -16.8409 | 1.0 | 17.2683 | -127.0178 | -35.3022 | -2.1602 | -2.1908 |
| 0.0 | 3.2 | 600 | 0.0000 | 0.4325 | -16.8850 | 1.0 | 17.3175 | -127.1649 | -35.2854 | -2.1601 | -2.1908 |
| 0.0 | 3.4667 | 650 | 0.0000 | 0.4328 | -16.9236 | 1.0 | 17.3564 | -127.2934 | -35.2844 | -2.1601 | -2.1908 |
| 0.0 | 3.7333 | 700 | 0.0000 | 0.4276 | -16.9224 | 1.0 | 17.3501 | -127.2896 | -35.3016 | -2.1593 | -2.1901 |
| 0.0 | 4.0 | 750 | 0.0000 | 0.4255 | -16.9406 | 1.0 | 17.3661 | -127.3502 | -35.3088 | -2.1599 | -2.1907 |
| 0.0 | 4.2667 | 800 | 0.0000 | 0.4318 | -16.9566 | 1.0 | 17.3883 | -127.4033 | -35.2878 | -2.1593 | -2.1901 |
| 0.0 | 4.5333 | 850 | 0.0000 | 0.4371 | -16.9488 | 1.0 | 17.3860 | -127.3775 | -35.2699 | -2.1592 | -2.1901 |
| 0.0 | 4.8 | 900 | 0.0000 | 0.4446 | -16.9496 | 1.0 | 17.3942 | -127.3800 | -35.2449 | -2.1592 | -2.1901 |
| 0.0 | 5.0667 | 950 | 0.0000 | 0.4441 | -16.9514 | 1.0 | 17.3955 | -127.3862 | -35.2466 | -2.1592 | -2.1901 |
| 0.0 | 5.3333 | 1000 | 0.0000 | 0.4441 | -16.9514 | 1.0 | 17.3955 | -127.3862 | -35.2466 | -2.1592 | -2.1901 |