SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fixing weights decay in run_squad example

Browse Source
This commit is contained in:
thomwolf
2018-11-20 10:12:44 +01:00
parent 061eeca84a
commit 6b2136a8a9
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/run_squad.py
View File

@@ -842,8 +842,8 @@ 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,