fixed_14
done · peak unseen_mismatch 90.5
Referenced by
α schedule
α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150 α 1.4 ×150
Figures
Results
accuracy by training iteration, mean ± sd over seeds · schedule ends at α = 1.4
seen_* probed at reference α = 1.4 · unseen_* = held-out pairings, uniform (α-independent) · 1000 pairs per condition
| iteration | seen_match | seen_mismatch | unseen_match | unseen_mismatch |
|---|---|---|---|---|
| 150 | 52.8 ± 3.6 | 49.1 ± 1.9 | 52.6 ± 3.6 | 47.6 ± 3.0 |
| 300 | 90.1 ± 19.2 | 38.8 ± 20.7 | 89.8 ± 19.6 | 39.0 ± 20.1 |
| 450 | 100.0 ± 0.0 | 46.0 ± 28.5 | 100.0 ± 0.0 | 46.8 ± 28.4 |
| 600 | 100.0 ± 0.0 | 36.1 ± 28.7 | 100.0 ± 0.0 | 37.1 ± 28.5 |
| 750 | 100.0 ± 0.1 | 51.6 ± 32.1 | 100.0 ± 0.0 | 52.4 ± 31.9 |
| 900 | 100.0 ± 0.1 | 74.6 ± 32.6 | 99.8 ± 0.5 | 72.5 ± 31.1 |
| 1050 | 99.9 ± 0.2 | 80.5 ± 26.6 | 99.2 ± 1.3 | 77.3 ± 25.7 |
| 1200 | 99.8 ± 0.3 | 91.5 ± 13.7 | 99.4 ± 0.9 | 88.6 ± 12.4 |
| 1350 | 99.8 ± 0.2 | 91.8 ± 15.1 | 99.0 ± 1.6 | 87.8 ± 13.5 |
| 1500 | 99.8 ± 0.3 | 91.0 ± 13.5 | 99.2 ± 1.0 | 86.6 ± 12.4 |
| 1650 | 99.8 ± 0.2 | 93.7 ± 6.6 | 98.8 ± 1.4 | 86.4 ± 8.6 |
| 1800 | 99.8 ± 0.2 | 97.0 ± 3.1 | 98.7 ± 1.4 | 90.5 ± 7.2 |
| 1950 | 99.9 ± 0.1 | 96.7 ± 3.4 | 97.8 ± 2.2 | 89.5 ± 7.6 |
| 2100 | 99.8 ± 0.2 | 96.1 ± 4.7 | 97.4 ± 2.7 | 86.0 ± 8.8 |
| 2250 | 99.8 ± 0.3 | 96.0 ± 3.1 | 96.5 ± 3.0 | 83.4 ± 8.5 |
| 2400 | 99.9 ± 0.1 | 96.5 ± 3.2 | 97.6 ± 1.4 | 86.0 ± 6.2 |