训练时出现的错误

[Garbobro]

我把数据集换成了完整的duie百度数据集，在训练的时候第一轮训练到10%时出错： Epoch 1/10: 10%|▉ | 10600/106960 [37:13<5:41:25, 4.70it/s, loss:0.09831] 0%| | 0/20652 [00:00<?, ?it/s] Traceback (most recent call last): File "C:\Users\Administrator\Desktop\NLP\CasRelPyTorch-master\Run.py", line 63, in trainer.train() File "D:\Anaconda3\lib\site-packages\fastNLP\core\trainer.py", line 622, in train raise e File "D:\Anaconda3\lib\site-packages\fastNLP\core\trainer.py", line 615, in train self._train() File "D:\Anaconda3\lib\site-packages\fastNLP\core\trainer.py", line 720, in _train self.callback_manager.on_epoch_end() File "D:\Anaconda3\lib\site-packages\fastNLP\core\callback.py", line 314, in wrapper returns.append(getattr(callback, func.name)(*arg)) File "C:\Users\Administrator\Desktop\NLP\CasRelPyTorch-master\model\callback.py", line 30, in on_epoch_end precision, recall, f1_score = metric(self.data_iter, self.rel_vocab, self.config, self.model) File "C:\Users\Administrator\Desktop\NLP\CasRelPyTorch-master\model\evaluate.py", line 71, in metric gold_triples = set(to_tuple(batch_y['triples'][0])) TypeError: unhashable type: 'dict'

Process finished with exit code 1 请问能解答一下哪里的问题吗，谢谢了

[yangsirui990402]

你好，我也遇到了这个问题，请问你解决了吗