phi3star
done · peak unseen_mismatch 97.9
Referenced by
α schedule
α 3.1993 ×25 α 3.155 ×25 α 3.0753 ×25 α 2.963 ×25 α 2.8198 ×25 α 2.6469 ×25 α 2.4453 ×25 α 2.2158 ×25 α 1.9588 ×25 α 1.675 ×25 α 1.3649 ×25 α 1.0288 ×25 α 0.6671 ×25 α 0.2802 ×25
Figures
Results
accuracy by training iteration, mean ± sd over seeds · schedule ends at α = 0.2802
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 ± 1.6 | 50.0 ± 1.6 | 50.1 ± 1.7 | 50.0 ± 1.6 |
| 50 | 51.3 ± 1.9 | 50.1 ± 1.7 | 50.2 ± 1.5 | 50.0 ± 1.6 |
| 75 | 52.0 ± 2.3 | 50.5 ± 1.8 | 50.6 ± 2.2 | 49.8 ± 1.6 |
| 100 | 57.3 ± 7.2 | 53.3 ± 4.6 | 53.2 ± 5.8 | 50.6 ± 2.8 |
| 125 | 68.9 ± 11.8 | 63.3 ± 9.9 | 61.7 ± 11.3 | 56.2 ± 7.8 |
| 150 | 82.1 ± 11.4 | 76.6 ± 11.0 | 73.1 ± 12.7 | 66.7 ± 10.7 |
| 175 | 89.1 ± 7.6 | 85.4 ± 7.6 | 79.6 ± 10.5 | 74.2 ± 9.3 |
| 200 | 93.0 ± 4.5 | 90.4 ± 4.6 | 83.9 ± 8.0 | 79.3 ± 7.5 |
| 225 | 95.5 ± 2.6 | 93.4 ± 2.7 | 87.2 ± 6.2 | 83.2 ± 6.2 |
| 250 | 97.6 ± 1.4 | 96.1 ± 1.7 | 91.4 ± 4.2 | 87.7 ± 4.5 |
| 275 | 99.1 ± 0.6 | 98.0 ± 1.0 | 95.5 ± 2.5 | 92.1 ± 3.6 |
| 300 | 99.8 ± 0.2 | 99.1 ± 1.2 | 98.6 ± 1.5 | 95.9 ± 3.7 |
| 325 | 100.0 ± 0.0 | 99.4 ± 2.0 | 99.9 ± 0.2 | 97.9 ± 4.3 |
| 350 | 100.0 ± 0.0 | 97.1 ± 7.2 | 100.0 ± 0.0 | 94.7 ± 10.2 |