← Back to Test-Time Training

score-first legal TTT

Test-Time Training
Used in
1 PRs
Best BPB
1.1157
Avg BPB
1.1157

Hyperparameters Across PRs

pr_numberparameters
841{"optimizer":"AdamW","chunk_size":131072,"epochs":3,"freeze_blocks":8,"learning_rate":0.0001,"weight_decay":0.01,"momentum":0.9}