s1_e0_blk
done · peak unseen_mismatch 59.5
α schedule
α 1.0 ×600 α 0.0 ×600
Figures
Results
accuracy by training iteration, mean ± sd over seeds · schedule ends at α = 0.0
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 | 32.9 ± 22.1 | 100.0 ± 0.0 | 33.5 ± 22.8 |
| 500 | 100.0 ± 0.0 | 45.8 ± 30.8 | 100.0 ± 0.0 | 46.8 ± 30.7 |
| 550 | 100.0 ± 0.0 | 47.6 ± 22.1 | 100.0 ± 0.0 | 48.1 ± 22.2 |
| 600 | 100.0 ± 0.0 | 52.0 ± 27.8 | 100.0 ± 0.0 | 53.1 ± 27.6 |
| 650 | 100.0 ± 0.0 | 59.1 ± 31.7 | 100.0 ± 0.0 | 59.5 ± 31.7 |
| 700 | 100.0 ± 0.0 | 46.3 ± 32.1 | 100.0 ± 0.0 | 46.9 ± 32.2 |
| 750 | 100.0 ± 0.0 | 41.1 ± 24.6 | 100.0 ± 0.0 | 41.3 ± 24.9 |
| 800 | 100.0 ± 0.0 | 46.7 ± 33.0 | 100.0 ± 0.0 | 46.6 ± 33.2 |
| 850 | 100.0 ± 0.0 | 35.3 ± 32.0 | 100.0 ± 0.0 | 34.6 ± 30.8 |
| 900 | 100.0 ± 0.0 | 43.6 ± 25.8 | 100.0 ± 0.0 | 43.7 ± 26.1 |
| 950 | 100.0 ± 0.0 | 23.1 ± 18.8 | 100.0 ± 0.0 | 22.6 ± 17.9 |
| 1000 | 100.0 ± 0.0 | 36.7 ± 36.7 | 100.0 ± 0.0 | 36.6 ± 36.4 |
| 1050 | 100.0 ± 0.0 | 39.8 ± 35.3 | 100.0 ± 0.0 | 39.9 ± 35.5 |
| 1100 | 100.0 ± 0.0 | 39.6 ± 39.5 | 100.0 ± 0.0 | 40.3 ± 40.0 |
| 1150 | 100.0 ± 0.0 | 33.0 ± 42.6 | 100.0 ± 0.0 | 33.4 ± 42.6 |
| 1200 | 100.0 ± 0.0 | 35.4 ± 30.3 | 100.0 ± 0.0 | 35.3 ± 30.1 |