271 B
271 B
| 1 | checkpoint | strict_accuracy | stale_law_violations | abstention_rate | safety_abstained |
|---|---|---|---|---|---|
| 2 | base (untrained) | 0.0081 | 12 | 0.37 | 2 |
| 3 | checkpoint-50 | 0.0081 | 1 | 0.424 | 2 |
| 4 | checkpoint-100 | 0.004 | 1 | 0.342 | 2 |
| 5 | checkpoint-150 | 0.0081 | 1 | 0.452 | 2 |
| 6 | checkpoint-197 | 0.0081 | 1 | 0.474 | 2 |
| 7 | final | 0.0081 | 1 | 0.474 | 2 |