Views
No views yet
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1452 | 1.0 | 3479 | 1.9266 |
| 2.0791 | 2.0 | 6958 | 1.8880 |
| 1.9458 | 3.0 | 10437 | 1.8700 |
| 2.0109 | 4.0 | 13916 | 1.8614 |
| 2.0050 | 5.0 | 17395 | 1.8584 |
| Metric | Results | Explained |
|---|---|---|
| BLEU | 13.711 | Matches exact word sequence referencing our ground truth and adapter output. |
| 0-20= translation is literal or broken, 20-50=good (sweet spot), >60=very good or identical training and test data. | ||
| chrF++ | 45.363 | Matches character sequence instead of whole words. |
| Model adapter is getting the root words and grammar concepts right but using different word variations or spellings than our ground truth. |