nlpyang / BertSum

Code for paper Fine-tune BERT for Extractive Summarization
Apache License 2.0
1.46k stars 422 forks source link

KeyError: 'paper_id' #94

Closed sayeedk06 closed 4 years ago

sayeedk06 commented 4 years ago

Whats the issue here? After running the python train.py command as in read me. This error shows up

[2020-04-21 12:36:18,824 INFO] * number of parameters: 109483009 [2020-04-21 12:36:18,824 INFO] Start training... [2020-04-21 12:36:18,827 INFO] Loading train dataset from ../bert_data/cnndm.train.123.bert.pt [2020-04-21 12:36:18,934 INFO] Loaded train dataset from ../bert_data/cnndm.train.123.bert.pt, number of examples: 2001 Traceback (most recent call last): File "train.py", line 395, in <module> train(args, device_id) File "train.py", line 323, in train trainer.train(train_iter_fct, args.train_steps) File "/content/drive/My Drive/i_have_no_idea/BertSum/src/models/trainer.py", line 142, in train for i, batch in enumerate(train_iter): File "/content/drive/My Drive/i_have_no_idea/BertSum/src/models/data_loader.py", line 175, in __iter__ for batch in self.cur_iter: File "/content/drive/My Drive/i_have_no_idea/BertSum/src/models/data_loader.py", line 274, in __iter__ for idx, minibatch in enumerate(self.batches): File "/content/drive/My Drive/i_have_no_idea/BertSum/src/models/data_loader.py", line 260, in create_batches for buffer in self.batch_buffer(data, self.batch_size * 50): File "/content/drive/My Drive/i_have_no_idea/BertSum/src/models/data_loader.py", line 243, in batch_buffer ex = self.preprocess(ex, self.is_test) File "/content/drive/My Drive/i_have_no_idea/BertSum/src/models/data_loader.py", line 231, in preprocess paper_id = ex['paper_id'] KeyError: 'paper_id'

namhkoh commented 1 year ago

How did you solve it?