ValueError                                Traceback (most recent call last)
File ~/PycharmProjects/nlp-env/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:707, in BatchEncoding.convert_to_tensors(self, tensor_type, prepend_batch_axis)
    706 if not is_tensor(value):
--> 707     tensor = as_tensor(value)
    709     # Removing this for now in favor of controlling the shape with `prepend_batch_axis`
    710     # # at-least2d
    711     # if tensor.ndim > 2:
    712     #     tensor = tensor.squeeze(0)
    713     # elif tensor.ndim < 2:
    714     #     tensor = tensor[None, :]

ValueError: too many dimensions 'str'

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
Input In [72], in <module>
----> 1 data_collator(features)

File ~/PycharmProjects/nlp-env/lib/python3.9/site-packages/transformers/data/data_collator.py:586, in DataCollatorForSeq2Seq.__call__(self, features, return_tensors)
    583         else:
    584             feature["labels"] = np.concatenate([remainder, feature["labels"]]).astype(np.int64)
--> 586 features = self.tokenizer.pad(
    587     features,
    588     padding=self.padding,
    589     max_length=self.max_length,
    590     pad_to_multiple_of=self.pad_to_multiple_of,
    591     return_tensors=return_tensors,
    592 )
    594 # prepare decoder_input_ids
    595 if (
    596     labels is not None
    597     and self.model is not None
    598     and hasattr(self.model, "prepare_decoder_input_ids_from_labels")
    599 ):

File ~/PycharmProjects/nlp-env/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:2842, in PreTrainedTokenizerBase.pad(self, encoded_inputs, padding, max_length, pad_to_multiple_of, return_attention_mask, return_tensors, verbose)
   2839             batch_outputs[key] = []
   2840         batch_outputs[key].append(value)
-> 2842 return BatchEncoding(batch_outputs, tensor_type=return_tensors)

File ~/PycharmProjects/nlp-env/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:212, in BatchEncoding.__init__(self, data, encoding, tensor_type, prepend_batch_axis, n_sequences)
    208     n_sequences = encoding[0].n_sequences
    210 self._n_sequences = n_sequences
--> 212 self.convert_to_tensors(tensor_type=tensor_type, prepend_batch_axis=prepend_batch_axis)

File ~/PycharmProjects/nlp-env/lib/python3.9/site-packages/transformers/tokenization_utils_base.py:723, in BatchEncoding.convert_to_tensors(self, tensor_type, prepend_batch_axis)
    718         if key == "overflowing_tokens":
    719             raise ValueError(
    720                 "Unable to create tensor returning overflowing tokens of different lengths. "
    721                 "Please see if a fast version of this tokenizer is available to have this feature available."
    722             )
--> 723         raise ValueError(
    724             "Unable to create tensor, you should probably activate truncation and/or padding "
    725             "with 'padding=True' 'truncation=True' to have batched tensors with the same length."
    726         )
    728 return self

ValueError: Unable to create tensor, you should probably activate truncation and/or padding with 'padding=True' 'truncation=True' to have batched tensors with the same length.