← Back to Test-Time Training
full TTT with SGD
Test-Time TrainingUsed in
1 PRs
Best BPB
1.1207
Avg BPB
1.1207
Submissions
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 577 | {"learning_rate":0.002,"epochs":3,"max_train_chunks":50,"EMA_decay":0,"freeze_blocks":2,"optimizer":"SGD"} |