Skip to content

GitLab

"...git@developer.sourcefind.cn:gaoqiong/flash-attention.git" did not exist on "c422fee3776eb3ea24e011ef641fd5fbeb212623"
Unverified Commit 6c4789e4 authored by xiaoda99's avatar xiaoda99 Committed by GitHub
Browse files

Fix ineffective no_decay bug

parent 956c9173
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
examples/run_classifier.py
View file @ 6c4789e4
......@@ -503,8 +503,8 @@ def main():
param_optimizer = list(model.named_parameters())
no_decay = ['bias', 'gamma', 'beta']
optimizer_grouped_parameters = [
{'params': [p for n, p in param_optimizer if n not in no_decay], 'weight_decay_rate': 0.01},
{'params': [p for n, p in param_optimizer if n in no_decay], 'weight_decay_rate': 0.0}
{'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay_rate': 0.01},
{'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay_rate': 0.0}
]
optimizer = BertAdam(optimizer_grouped_parameters,
lr=args.learning_rate,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment