I am getting a KeyError when I run any of the setting (extractive/abstractive). Has anyone come across this? I have all the .pt datasets and it is loading all of them as you can see in the first part of the log file.

[2021-12-03 04:00:45,621 INFO] loading file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt from cache at ../temp/26bc1ad6c0ac742e9b52263248f6d0f00068293b33709fae12320c0e35ccfbbb.542ce4285a40d23a559526243235df47c5f75c197f04f37d1a0c124c32c9a084
gpu_rank 0
[2021-12-03 04:00:45,654 INFO] * number of parameters: 75951418
[2021-12-03 04:00:45,655 INFO] Start training...
[2021-12-03 04:00:45,766 INFO] Loading train dataset from ../bert_data/cnndm.train.18.bert.pt, number of examples: 1998
Traceback (most recent call last):
File "train.py", line 122, in
train_abs(args, device_id)
File "/content/PreSumm/src/train_abstractive.py", line 273, in train_abs
train_abs_single(args, device_id)
File "/content/PreSumm/src/train_abstractive.py", line 334, in train_abs_single
trainer.train(train_iter_fct, args.train_steps)
File "/content/PreSumm/src/models/trainer.py", line 142, in train
for i, batch in enumerate(train_iter):
File "/content/PreSumm/src/models/data_loader.py", line 142, in iter
for batch in self.cur_iter:
File "/content/PreSumm/src/models/data_loader.py", line 278, in iter
for idx, minibatch in enumerate(self.batches):
File "/content/PreSumm/src/models/data_loader.py", line 256, in create_batches
for buffer in self.batch_buffer(data, self.batch_size * 300):
File "/content/PreSumm/src/models/data_loader.py", line 224, in batch_buffer
ex = self.preprocess(ex, self.is_test)
File "/content/PreSumm/src/models/data_loader.py", line 195, in preprocess
tgt = ex['tgt'][:self.args.max_tgt_len][:-1]+[2]
KeyError: 'tgt'