python main.py --model Transformer --cuda and get a user warning

chenxie95 / deeplearning_course_sjtu

14 stars 2 forks source link

python main.py --model Transformer --cuda and get a user warning #30

Closed rujiangyouyou closed 6 months ago

rujiangyouyou commented 7 months ago

UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance) warnings.warn(f"enable_nested_tensor is True, but self.use_nested_tensor is False because {why_not_sparsity_fast_path}")

Will this affect the model performance?

chenxie95 commented 7 months ago

It won't affect model performance, only affect the speed. In this LM project, the training and inference is quite fast so it won't bring about related issues.