diff --git a/examples/run_swag.py b/examples/run_swag.py index 5e7ac85c63..59bb9866c3 100644 --- a/examples/run_swag.py +++ b/examples/run_swag.py @@ -390,7 +390,7 @@ def main(): # hack to remove pooler, which is not used # thus it produce None grad that break apex - param_optimizer = [n for n in param_optimizer if 'pooler' not in n[0]] + param_optimizer = [n for n in param_optimizer] no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight'] optimizer_grouped_parameters = [