Quasi-Attention-ABSA

Quasi-Attention-ABSA copied to clipboard

bad results when use models downloaded from huggingface

1

Hi, I try to reproduct your work with pytorch BERT model download from huggingface, only to get a very bad result, the training loss keeps around 1.0 in the first...

beanandrew

代码结果不好

3

您好，我复现了您的代码，为什么和论文中的结果差距很大，甚至说模型就是无效的，我没有改动您的代码，直接运行的 以下是 CGBERT模型epoch = 29的结果 > `05/07/2021 01:46:20 - INFO - util.train_helper - epoch = 29████████████████████████████▌| 312/314 [00:05 > 05/07/2021 01:46:20 - INFO - util.train_helper - loss = 1.0986090652494622 >...

geekbeing

Katherine536