s3_e1_blk
done · peak unseen_mismatch 95.5
α schedule
α 3.0 ×400 α 2.0 ×400 α 1.0 ×400
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 | 51.3 ± 2.2 | 49.6 ± 0.8 | 50.0 ± 1.7 | 50.3 ± 1.6 |
| 100 | 55.9 ± 7.4 | 53.6 ± 4.6 | 52.7 ± 5.7 | 50.5 ± 3.7 |
| 150 | 76.3 ± 12.5 | 72.0 ± 11.7 | 69.1 ± 13.0 | 63.1 ± 11.1 |
| 200 | 88.2 ± 4.3 | 86.4 ± 4.6 | 78.2 ± 8.2 | 75.1 ± 6.9 |
| 250 | 90.7 ± 1.6 | 89.4 ± 1.6 | 79.0 ± 4.9 | 76.2 ± 3.6 |
| 300 | 91.8 ± 1.5 | 90.3 ± 1.5 | 78.3 ± 4.3 | 75.5 ± 4.1 |
| 350 | 91.7 ± 1.0 | 90.3 ± 1.2 | 77.0 ± 3.1 | 73.9 ± 2.3 |
| 400 | 92.6 ± 1.2 | 90.7 ± 1.6 | 79.5 ± 5.0 | 74.6 ± 4.8 |
| 450 | 96.4 ± 0.8 | 94.2 ± 1.4 | 85.5 ± 4.0 | 79.3 ± 4.9 |
| 500 | 97.2 ± 0.9 | 95.3 ± 1.2 | 87.8 ± 2.3 | 82.0 ± 3.7 |
| 550 | 97.6 ± 1.3 | 96.2 ± 1.3 | 88.0 ± 4.3 | 82.6 ± 6.0 |
| 600 | 97.6 ± 0.7 | 95.9 ± 0.8 | 88.7 ± 3.4 | 82.0 ± 4.5 |
| 650 | 98.2 ± 0.7 | 96.7 ± 1.0 | 90.8 ± 2.8 | 83.7 ± 5.5 |
| 700 | 98.0 ± 0.7 | 96.6 ± 0.7 | 91.2 ± 2.2 | 83.6 ± 3.9 |
| 750 | 97.9 ± 1.0 | 96.3 ± 0.9 | 90.3 ± 3.9 | 82.7 ± 3.8 |
| 800 | 98.4 ± 0.7 | 97.2 ± 1.0 | 92.2 ± 1.9 | 85.5 ± 5.0 |
| 850 | 100.0 ± 0.1 | 99.7 ± 0.3 | 98.9 ± 0.8 | 95.5 ± 3.9 |
| 900 | 100.0 ± 0.0 | 99.7 ± 0.3 | 99.1 ± 0.7 | 94.6 ± 5.0 |
| 950 | 100.0 ± 0.0 | 99.5 ± 0.6 | 99.6 ± 0.6 | 92.4 ± 6.7 |
| 1000 | 100.0 ± 0.0 | 99.4 ± 0.6 | 99.6 ± 0.2 | 92.0 ± 7.8 |
| 1050 | 100.0 ± 0.1 | 98.7 ± 1.6 | 99.0 ± 0.7 | 87.5 ± 11.8 |
| 1100 | 100.0 ± 0.1 | 98.7 ± 1.3 | 99.3 ± 0.6 | 85.8 ± 11.9 |
| 1150 | 100.0 ± 0.0 | 98.6 ± 1.1 | 98.7 ± 0.9 | 85.1 ± 10.6 |
| 1200 | 100.0 ± 0.0 | 98.2 ± 1.6 | 99.1 ± 0.8 | 83.3 ± 11.5 |