bert.embeddings.word_embeddings的尺寸不匹配。

Question

RuntimeError：bertforrelationExtraction的加载state_dict中的错误： bert.embeddings.word_embeddings的尺寸不匹配。

Traceback (most recent call last):
  File "main.py", line 248, in <module>
    result = trainer.predict(tokenizer, text, id2label, args, ids)
  File "main.py", line 146, in predict
    model, optimizer, epoch, loss = self.load_ckp(model, optimizer, checkpoint)
  File "main.py", line 38, in load_ckp
    model.load_state_dict(checkpoint['state_dict'])
  File "C:\Anaconda3\envs\NLP_Research\lib\site-packages\torch\nn\modules\module.py", line 1045, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for BertForRelationExtraction:
        size mismatch for bert.embeddings.word_embeddings.weight: copying a param with shape torch.Size([21128, 768]) from checkpoint, the shape in current model is torch.Size([30522, 768]).