Views
No views yet
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Input Tokens Seen |
|---|---|---|---|---|---|
| No log | 0 | 0 | 2.6550 | 0.2394 | 0 |
| 1.8381 | 0.6329 | 50 | 2.1300 | 0.1268 | 409600 |
| 1.8597 | 1.2658 | 100 | 1.6786 | 0.1972 | 819200 |
| 1.694 | 1.8987 | 150 | 1.6346 | 0.2113 | 1228800 |
| 1.586 | 2.5316 | 200 | 1.6395 | 0.1408 | 1638400 |