burst_16
done · peak unseen_mismatch 95.1
Referenced by
α schedule
α 5.0 ×25 α 5.0 ×25 α 5.0 ×25 α 0.7 ×25 α 0.7 ×25 α 3.1429 ×25 α 3.1429 ×25 α 3.1429 ×25 α 0.7 ×25 α 0.7 ×25 α 0.7 ×25 α 1.2857 ×25 α 1.2857 ×25 α 0.7 ×25 α 0.7 ×25 α 0.7 ×25
Figures
Results
accuracy by training iteration, mean ± sd over seeds · schedule ends at α = 0.7
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 |
|---|---|---|---|---|
| 25 | 51.1 ± 1.5 | 50.1 ± 1.5 | 50.1 ± 1.7 | 50.0 ± 1.6 |
| 50 | 51.6 ± 1.9 | 50.1 ± 1.7 | 50.2 ± 1.5 | 49.9 ± 1.5 |
| 75 | 53.6 ± 3.3 | 51.7 ± 2.4 | 50.9 ± 2.4 | 49.9 ± 1.6 |
| 100 | 56.1 ± 8.0 | 51.4 ± 3.2 | 53.4 ± 7.4 | 50.2 ± 2.7 |
| 125 | 65.4 ± 15.5 | 50.9 ± 6.2 | 63.4 ± 15.7 | 49.8 ± 5.9 |
| 150 | 83.7 ± 17.0 | 66.5 ± 14.7 | 81.4 ± 18.3 | 63.7 ± 14.6 |
| 175 | 93.4 ± 10.3 | 84.7 ± 13.1 | 91.2 ± 12.1 | 81.3 ± 13.8 |
| 200 | 95.7 ± 6.0 | 91.6 ± 7.7 | 92.7 ± 8.2 | 86.9 ± 9.5 |
| 225 | 99.5 ± 4.2 | 94.8 ± 10.3 | 99.3 ± 4.7 | 94.1 ± 10.5 |
| 250 | 99.7 ± 3.5 | 91.7 ± 14.8 | 99.7 ± 3.9 | 91.1 ± 14.8 |
| 275 | 99.9 ± 0.8 | 90.3 ± 16.7 | 99.9 ± 1.3 | 89.7 ± 16.8 |
| 300 | 100.0 ± 0.1 | 94.5 ± 12.7 | 99.9 ± 0.4 | 93.7 ± 12.9 |
| 325 | 99.9 ± 0.1 | 96.1 ± 10.4 | 99.8 ± 0.4 | 95.1 ± 10.3 |
| 350 | 100.0 ± 0.0 | 95.1 ± 14.0 | 100.0 ± 0.0 | 94.9 ± 13.9 |
| 375 | 100.0 ± 0.1 | 93.9 ± 14.3 | 100.0 ± 0.2 | 93.3 ± 14.2 |
| 400 | 100.0 ± 0.0 | 93.4 ± 16.0 | 100.0 ± 0.0 | 92.8 ± 15.6 |