IndexError: tuple index out of range

from transformers import AutoModelForMaskedLM
self.xlm_roberta = AutoModelForMaskedLM.from_pretrained(“xlm-roberta-base”)

When I changed the model like this, I got an error.
I don’t really know what I can do to improve it.


IndexError Traceback (most recent call last)
in
4 print(f’FOLD: {fold}’)
5 print(’-’*50)
----> 6 run(train, fold)

in run(data, fold)
18 result_dict = trainer.train(
19 args, train_dataloader,
—> 20 epoch, result_dict
21 )
22 torch.cuda.synchronize()

in train(self, args, train_dataloader, epoch, result_dict)
32 outputs_start, outputs_end = self.model(
33 input_ids=input_ids,
—> 34 attention_mask=attention_mask,
35 )
36

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
→ 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),

in forward(self, input_ids, attention_mask)
32
33 sequence_output = outputs[0]
—> 34 pooled_output = outputs[1]
35
36 # sequence_output = self.dropout(sequence_output)

/opt/conda/lib/python3.7/site-packages/transformers/file_utils.py in getitem(self, k)
1738 return inner_dict[k]
1739 else:
→ 1740 return self.to_tuple()[k]
1741
1742 def setattr(self, name, value):

IndexError: tuple index out of range

Model code

Model