← Back to Test-Time Training
SGD TTT
Test-Time TrainingUsed in
2 PRs
Best BPB
1.0857
Avg BPB
1.1032
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 533 | {"learning_rate":0.002,"epochs":3,"freeze_blocks":2,"max_train_chunks":50,"ema_decay":0} |
| 1714 | {"epochs_per_chunk":3,"momentum":0.9,"score_before_update":true} |