← Back to Weight Averaging
LAWA
Weight AveragingUsed in
2 PRs
Best BPB
1.2302
Avg BPB
1.4337
Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 130 | {"start_frac":0.8,"checkpoint_interval_steps":200,"avg_last_fraction":0.2} |
| 675 | {"warmdown_checkpoints":"12-13"} |