s0_e1_blk
done · peak unseen_mismatch 83.0
α schedule
α 0.0 ×600 α 1.0 ×600
Figures
Results
accuracy by training iteration, mean ± sd over seeds · schedule ends at α = 1.0
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 | 50.4 ± 1.6 | 49.9 ± 1.1 | 49.8 ± 1.9 | 49.6 ± 1.9 |
| 100 | 50.3 ± 1.4 | 50.1 ± 2.2 | 49.8 ± 1.5 | 50.0 ± 1.9 |
| 150 | 52.9 ± 4.9 | 48.8 ± 3.2 | 53.3 ± 5.4 | 47.9 ± 2.6 |
| 200 | 57.3 ± 16.0 | 44.2 ± 13.4 | 57.9 ± 15.6 | 45.0 ± 14.2 |
| 250 | 68.8 ± 21.0 | 44.6 ± 11.9 | 68.0 ± 20.9 | 45.0 ± 11.8 |
| 300 | 80.4 ± 24.0 | 39.6 ± 13.0 | 80.6 ± 23.8 | 40.6 ± 12.5 |
| 350 | 92.7 ± 15.7 | 28.9 ± 16.1 | 92.4 ± 16.4 | 29.4 ± 15.0 |
| 400 | 97.6 ± 7.1 | 18.9 ± 18.1 | 97.5 ± 7.6 | 19.4 ± 18.5 |
| 450 | 100.0 ± 0.0 | 41.7 ± 26.0 | 100.0 ± 0.0 | 41.4 ± 26.0 |
| 500 | 100.0 ± 0.0 | 44.5 ± 30.4 | 100.0 ± 0.0 | 44.3 ± 29.9 |
| 550 | 100.0 ± 0.0 | 37.8 ± 31.9 | 100.0 ± 0.0 | 38.1 ± 32.3 |
| 600 | 100.0 ± 0.0 | 29.3 ± 30.8 | 100.0 ± 0.0 | 30.0 ± 30.7 |
| 650 | 100.0 ± 0.0 | 33.7 ± 34.4 | 100.0 ± 0.0 | 34.2 ± 34.3 |
| 700 | 100.0 ± 0.0 | 37.4 ± 35.9 | 100.0 ± 0.0 | 38.1 ± 35.9 |
| 750 | 100.0 ± 0.0 | 40.4 ± 29.7 | 100.0 ± 0.0 | 40.9 ± 29.5 |
| 800 | 100.0 ± 0.0 | 35.5 ± 36.2 | 100.0 ± 0.0 | 35.2 ± 36.5 |
| 850 | 100.0 ± 0.0 | 35.2 ± 36.3 | 100.0 ± 0.0 | 35.5 ± 35.6 |
| 900 | 100.0 ± 0.0 | 34.1 ± 34.2 | 100.0 ± 0.0 | 34.1 ± 33.7 |
| 950 | 100.0 ± 0.0 | 48.4 ± 27.1 | 100.0 ± 0.0 | 47.5 ± 26.7 |
| 1000 | 100.0 ± 0.0 | 40.5 ± 34.6 | 100.0 ± 0.0 | 40.2 ± 34.7 |
| 1050 | 100.0 ± 0.0 | 57.8 ± 31.0 | 100.0 ± 0.0 | 57.1 ± 30.8 |
| 1100 | 100.0 ± 0.0 | 51.0 ± 25.0 | 100.0 ± 0.0 | 50.6 ± 24.8 |
| 1150 | 100.0 ± 0.0 | 69.5 ± 25.5 | 100.0 ± 0.0 | 68.9 ± 25.9 |
| 1200 | 100.0 ± 0.0 | 83.6 ± 20.2 | 100.0 ± 0.0 | 83.0 ± 20.2 |