s5_e3_blk
done · peak unseen_mismatch 74.1
α schedule
α 5.0 ×400 α 4.0 ×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 | 51.8 ± 2.1 | 49.9 ± 1.2 | 50.2 ± 1.8 | 50.0 ± 1.4 |
| 100 | 59.6 ± 6.4 | 56.9 ± 4.6 | 52.8 ± 3.7 | 51.7 ± 3.0 |
| 150 | 76.5 ± 5.5 | 74.3 ± 5.6 | 62.2 ± 5.9 | 59.1 ± 4.4 |
| 200 | 79.5 ± 1.9 | 78.0 ± 2.0 | 60.5 ± 3.5 | 59.9 ± 3.0 |
| 250 | 79.8 ± 1.8 | 78.6 ± 1.6 | 60.5 ± 3.1 | 59.4 ± 3.1 |
| 300 | 82.4 ± 1.6 | 81.0 ± 1.8 | 63.4 ± 3.6 | 62.4 ± 3.8 |
| 350 | 83.8 ± 2.3 | 82.1 ± 2.2 | 65.8 ± 5.6 | 65.2 ± 5.9 |
| 400 | 83.3 ± 1.7 | 81.8 ± 1.5 | 64.7 ± 2.3 | 62.0 ± 3.1 |
| 450 | 86.4 ± 1.2 | 84.3 ± 2.1 | 67.8 ± 5.2 | 64.1 ± 4.5 |
| 500 | 86.3 ± 1.9 | 84.5 ± 2.3 | 67.3 ± 4.0 | 64.2 ± 3.8 |
| 550 | 87.2 ± 1.8 | 85.6 ± 2.2 | 68.5 ± 6.2 | 64.1 ± 6.3 |
| 600 | 87.5 ± 1.9 | 86.1 ± 2.1 | 68.7 ± 4.1 | 64.6 ± 3.9 |
| 650 | 88.4 ± 1.7 | 86.6 ± 1.7 | 68.9 ± 4.2 | 64.7 ± 4.4 |
| 700 | 88.5 ± 1.4 | 86.5 ± 1.4 | 69.2 ± 3.2 | 64.8 ± 2.5 |
| 750 | 88.4 ± 1.3 | 86.5 ± 1.4 | 69.8 ± 3.0 | 65.4 ± 2.3 |
| 800 | 88.8 ± 1.5 | 87.2 ± 1.4 | 71.0 ± 3.1 | 66.1 ± 2.8 |
| 850 | 92.2 ± 1.1 | 90.1 ± 1.7 | 77.2 ± 3.6 | 71.3 ± 4.4 |
| 900 | 92.0 ± 1.5 | 90.2 ± 1.9 | 74.9 ± 5.5 | 70.3 ± 6.0 |
| 950 | 93.0 ± 1.2 | 90.8 ± 1.3 | 77.6 ± 4.8 | 71.3 ± 6.2 |
| 1000 | 93.3 ± 1.1 | 91.6 ± 1.0 | 78.8 ± 4.0 | 72.6 ± 4.9 |
| 1050 | 93.1 ± 1.4 | 91.0 ± 1.5 | 77.4 ± 3.3 | 71.8 ± 4.0 |
| 1100 | 93.6 ± 0.9 | 92.1 ± 1.3 | 79.3 ± 4.8 | 73.9 ± 4.9 |
| 1150 | 93.9 ± 1.3 | 91.8 ± 1.4 | 79.1 ± 4.0 | 74.1 ± 5.2 |
| 1200 | 93.7 ± 1.1 | 92.4 ± 0.9 | 79.8 ± 3.8 | 74.1 ± 3.3 |