Skip to content

GitLab

Unverified Commit 061eeca8 authored by Thomas Wolf's avatar Thomas Wolf Committed by GitHub
Browse files

Merge pull request #32 from xiaoda99/master 

Fix ineffective no_decay bug when using BERTAdam
parents fd32ebed 6c4789e4
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
examples/run_classifier.py
View file @ 061eeca8
...@@ -503,8 +503,8 @@ def main(): ...@@ -503,8 +503,8 @@ def main():
param_optimizer = list(model.named_parameters()) param_optimizer = list(model.named_parameters())
no_decay = ['bias', 'gamma', 'beta'] no_decay = ['bias', 'gamma', 'beta']
optimizer_grouped_parameters = [ 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 not any(nd in n for nd 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 any(nd in n for nd in no_decay)], 'weight_decay_rate': 0.0}
] ]
optimizer = BertAdam(optimizer_grouped_parameters, optimizer = BertAdam(optimizer_grouped_parameters,
lr=args.learning_rate, 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