free-5411cbfe
done · peak unseen_mismatch 99.0
α schedule
α 4.761 ×160 α 0.8109 ×140 α 0.8109 ×100
Results
accuracy by training iteration, mean ± sd over seeds · schedule ends at α = 0.8109
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 |
|---|---|---|---|---|
| 100 | 61.9 ± 9.1 | 57.9 ± 7.2 | 54.8 ± 7.0 | 51.7 ± 4.4 |
| 110 | 65.8 ± 9.9 | 61.6 ± 9.0 | 57.2 ± 8.1 | 53.6 ± 5.9 |
| 120 | 70.6 ± 9.4 | 66.6 ± 9.0 | 59.7 ± 8.2 | 56.3 ± 6.4 |
| 130 | 74.9 ± 8.3 | 71.3 ± 7.9 | 62.2 ± 9.0 | 58.6 ± 7.1 |
| 140 | 77.8 ± 6.9 | 74.4 ± 6.6 | 63.9 ± 8.6 | 60.6 ± 7.2 |
| 150 | 80.0 ± 5.3 | 77.0 ± 5.3 | 65.1 ± 8.3 | 62.2 ± 7.0 |
| 160 | 80.6 ± 4.4 | 77.9 ± 4.6 | 65.3 ± 7.3 | 62.6 ± 6.2 |
| 170 | 84.4 ± 5.2 | 81.7 ± 5.1 | 71.0 ± 8.3 | 67.6 ± 7.5 |
| 180 | 91.9 ± 5.3 | 89.3 ± 5.6 | 84.6 ± 9.0 | 80.5 ± 9.0 |
| 190 | 97.3 ± 2.8 | 95.1 ± 3.9 | 94.4 ± 5.6 | 91.1 ± 6.5 |
| 200 | 98.5 ± 2.4 | 95.7 ± 3.9 | 97.1 ± 3.9 | 92.6 ± 5.1 |
| 210 | 99.6 ± 0.6 | 94.6 ± 4.5 | 98.9 ± 1.2 | 92.8 ± 3.9 |
| 220 | 100.0 ± 0.0 | 77.8 ± 15.2 | 100.0 ± 0.1 | 76.1 ± 12.0 |
| 230 | 100.0 ± 0.0 | 84.3 ± 12.2 | 99.5 ± 0.5 | 84.8 ± 10.8 |
| 240 | 100.0 ± 0.0 | 51.9 ± 0.0 | 100.0 ± 0.0 | 50.9 ± 0.0 |
| 250 | 100.0 ± 0.0 | 50.7 ± 0.0 | 100.0 ± 0.0 | 50.2 ± 0.0 |
| 260 | 100.0 ± 0.0 | 49.4 ± 0.0 | 100.0 ± 0.0 | 49.0 ± 0.0 |
| 270 | 100.0 ± 0.0 | 54.9 ± 0.0 | 100.0 ± 0.0 | 53.7 ± 0.0 |
| 280 | 100.0 ± 0.0 | 70.7 ± 0.0 | 100.0 ± 0.0 | 71.8 ± 0.0 |
| 290 | 100.0 ± 0.0 | 60.6 ± 0.0 | 100.0 ± 0.0 | 59.2 ± 0.0 |
| 300 | 100.0 ± 0.0 | 70.8 ± 0.0 | 100.0 ± 0.0 | 70.4 ± 0.0 |
| 310 | 100.0 ± 0.0 | 82.9 ± 0.0 | 100.0 ± 0.0 | 81.8 ± 0.0 |
| 320 | 100.0 ± 0.0 | 62.1 ± 0.0 | 100.0 ± 0.0 | 61.3 ± 0.0 |
| 330 | 100.0 ± 0.0 | 57.0 ± 0.0 | 100.0 ± 0.0 | 55.3 ± 0.0 |
| 340 | 100.0 ± 0.0 | 91.0 ± 0.0 | 100.0 ± 0.0 | 92.0 ± 0.0 |
| 350 | 100.0 ± 0.0 | 99.7 ± 0.0 | 100.0 ± 0.0 | 99.0 ± 0.0 |