← Back to LR Schedule
fixed learning rates
LR ScheduleUsed in
1 PRs
Best BPB
1.1442
Avg BPB
1.1442
Submissions
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 317 | {"matrix_lr":0.025,"scalar_lr":0.025,"tied_embed_lr":0.035} |