我换成中文数据集，出现这个错误，请问是啥情况，是bert的原因吗 about spn4re

[DianboWork]

建议把错误报全

[ysgncss]

=== Epoch 0 train ===
Traceback (most recent call last):
File "C:/Users/kdecm/Desktop/临时文件/SPN4RE-main/main.py", line 100, in
trainer.train_model()
File "C:\Users\kdecm\Desktop\临时文件\SPN4RE-main\trainer\trainer.py", line 77, in train_model
loss, _ = self.model(input_ids, attention_mask, targets)
File "D:\anaconda3\envs\python37\lib\site-packages\torch\nn\modules\module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "C:\Users\kdecm\Desktop\临时文件\SPN4RE-main\models\setpred4RE.py", line 22, in forward
last_hidden_state, pooler_output = self.encoder(input_ids, attention_mask)
File "D:\anaconda3\envs\python37\lib\site-packages\torch\nn\modules\module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "C:\Users\kdecm\Desktop\临时文件\SPN4RE-main\models\seq_encoder.py", line 17, in forward
last_hidden_state, pooler_output = self.bert(input_ids, attention_mask=attention_mask)
File "D:\anaconda3\envs\python37\lib\site-packages\torch\nn\modules\module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "D:\anaconda3\envs\python37\lib\site-packages\transformers\modeling_bert.py", line 783, in forward
input_ids=input_ids, position_ids=position_ids, token_type_ids=token_type_ids, inputs_embeds=inputs_embeds
File "D:\anaconda3\envs\python37\lib\site-packages\torch\nn\modules\module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "D:\anaconda3\envs\python37\lib\site-packages\transformers\modeling_bert.py", line 174, in forward
position_embeddings = self.position_embeddings(position_ids)
File "D:\anaconda3\envs\python37\lib\site-packages\torch\nn\modules\module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "D:\anaconda3\envs\python37\lib\site-packages\torch\nn\modules\sparse.py", line 114, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "D:\anaconda3\envs\python37\lib\site-packages\torch\nn\functional.py", line 1724, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
IndexError: index out of range in self

[DianboWork]

torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse) 这里出错了，检查一下input_ids

[ysgncss]

貌似没啥问题呢

[ysgncss]

解决了。把data/generated_data目录下的文件删除了就好了 . 感谢大佬！

[ysgncss]

如果我想进行在线测试，输入句子输出所有的三元组，我应该怎么做？