Batch[k] = torch.tensor([f[k] for f in features]) ValueError: expected sequence of length 3 at dim 1 (got 4)

Beginners
1

Hi there,

I am trying to build a multiple-choice question solver and I am getting the following error.
Any thoughts what could be the cause of this error?

  File "../src/run_multiple_choice.py", line 195, in main
    model_path=model_args.model_name_or_path if os.path.isdir(model_args.model_name_or_path) else None
  File "/usr/local/lib/python3.7/site-packages/transformers/trainer.py", line 755, in train
    for step, inputs in enumerate(epoch_iterator):
  File "/usr/local/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 363, in __next__
    data = self._next_data()
  File "/usr/local/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 403, in _next_data
    data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
  File "/usr/local/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
    return self.collate_fn(data)
  File "/usr/local/lib/python3.7/site-packages/transformers/data/data_collator.py", line 65, in default_data_collator
    batch[k] = torch.tensor([f[k] for f in features])
ValueError: expected sequence of length 3 at dim 1 (got 4)
2

Looks like my instances were not of the same size. Making them the same size fixes the problem.

3

Hi, I’m running into the same problem. Processing for my custom multiple choice question answering task throws the same value error. Do you mind explaining how you resolved this problem?

4

I just fixed this error by setting my tokenizer’s padding to ‘max_length’.

1 Like
5

hi, how can I run the multi choice QA model if I have only two labels (1 and 2). when I am passing num_labels=2 in the AutoModelForMultipleChoice, the logits are having dims (nx4), but I need (nx2) since I have only two labels. How can I solve this problem?

tutorial I referred: Multiple choice
dataset used: art · Datasets at Hugging Face

6

This is solved. Thanks

7

I solved using. padding=‘max_length’ on tokens = tokenizer(text ,padding=‘max_length’)