← Back to LR Schedule

linear warmup

LR Schedule
Used in
14 PRs
Best BPB
1.0587
Avg BPB
1.3378

Hyperparameters Across PRs

pr_numberparameters
46{"warmup_steps":100}
536{"warmup_steps":30}
896{"warmup_steps":200}
1125{"warmup_steps":20}
1163{"warmup_steps":20}
1203{"warmup_steps":5}
1239{"warmup_fraction":0.2}
1691{"warmup_steps":20}
1842{"warmup_steps":500}
1866{"start_step":0,"end_step":500}
1876{"steps":20}
1880{"warmup_steps":20}
1891{"warmup_steps":1}
1919{"warmup_chunks":100}