s1_e3_blk
done · peak unseen_mismatch 96.0
α schedule
α 1.0 ×400 α 2.0 ×400 α 3.0 ×400
Figures
Results
accuracy by training iteration, mean ± sd over seeds · schedule ends at α = 3.0
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 |
|---|---|---|---|---|
| 50 | 50.6 ± 1.3 | 49.1 ± 0.7 | 50.0 ± 2.0 | 50.2 ± 1.2 |
| 100 | 50.1 ± 1.7 | 50.3 ± 2.2 | 50.3 ± 1.8 | 50.0 ± 1.8 |
| 150 | 51.2 ± 1.8 | 49.7 ± 1.9 | 51.1 ± 1.2 | 48.5 ± 1.1 |
| 200 | 57.8 ± 15.6 | 46.8 ± 8.9 | 58.3 ± 15.1 | 47.6 ± 9.7 |
| 250 | 71.9 ± 20.1 | 41.9 ± 10.9 | 72.1 ± 19.3 | 41.2 ± 9.8 |
| 300 | 88.1 ± 18.5 | 32.0 ± 21.6 | 88.1 ± 17.7 | 32.5 ± 20.6 |
| 350 | 100.0 ± 0.0 | 39.0 ± 27.4 | 100.0 ± 0.0 | 39.3 ± 27.7 |
| 400 | 100.0 ± 0.0 | 36.4 ± 24.8 | 100.0 ± 0.0 | 36.3 ± 25.2 |
| 450 | 100.0 ± 0.0 | 47.1 ± 30.5 | 100.0 ± 0.0 | 47.2 ± 30.2 |
| 500 | 100.0 ± 0.0 | 68.4 ± 23.7 | 100.0 ± 0.0 | 68.4 ± 24.2 |
| 550 | 100.0 ± 0.1 | 71.9 ± 30.3 | 99.7 ± 0.7 | 72.7 ± 29.0 |
| 600 | 99.9 ± 0.3 | 77.6 ± 30.1 | 99.6 ± 1.1 | 77.5 ± 29.4 |
| 650 | 99.8 ± 0.4 | 88.2 ± 20.4 | 99.6 ± 1.0 | 87.6 ± 19.9 |
| 700 | 99.4 ± 0.8 | 96.3 ± 4.1 | 98.7 ± 2.1 | 94.8 ± 4.5 |
| 750 | 99.0 ± 0.9 | 98.4 ± 1.1 | 97.9 ± 1.7 | 96.0 ± 2.4 |
| 800 | 98.7 ± 0.8 | 98.3 ± 1.2 | 96.5 ± 2.6 | 95.5 ± 2.8 |
| 850 | 96.8 ± 1.5 | 95.4 ± 2.0 | 90.8 ± 3.2 | 89.1 ± 2.4 |
| 900 | 95.3 ± 1.6 | 94.5 ± 2.3 | 88.3 ± 3.0 | 87.3 ± 2.8 |
| 950 | 94.6 ± 1.2 | 93.5 ± 1.7 | 86.1 ± 2.4 | 84.2 ± 2.1 |
| 1000 | 93.5 ± 1.3 | 92.5 ± 1.8 | 83.4 ± 3.1 | 82.0 ± 3.1 |
| 1050 | 92.4 ± 1.0 | 91.6 ± 1.3 | 81.3 ± 2.6 | 80.3 ± 2.9 |
| 1100 | 92.2 ± 1.1 | 91.7 ± 1.2 | 81.2 ± 3.4 | 80.0 ± 3.6 |
| 1150 | 91.9 ± 0.7 | 91.2 ± 1.0 | 80.0 ± 3.7 | 78.7 ± 2.7 |
| 1200 | 91.7 ± 1.0 | 91.0 ± 0.9 | 79.5 ± 2.7 | 77.7 ± 3.4 |