Hello, I am trying to use the tutorial here, Google Colab and I’m finetuning it on a custom dataset. I am loading my dataset from a pandas dataframe and I’m not sure what the error means here. Can anyone help me with this? TIA!
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ in <cell line: 21>:21 │
│ │
│ /usr/local/lib/python3.10/dist-packages/transformers/trainer.py:1664 in train │
│ │
│ 1661 │ │ inner_training_loop = find_executable_batch_size( │
│ 1662 │ │ │ self._inner_training_loop, self._train_batch_size, args.auto_find_batch_size │
│ 1663 │ │ ) │
│ ❱ 1664 │ │ return inner_training_loop( │
│ 1665 │ │ │ args=args, │
│ 1666 │ │ │ resume_from_checkpoint=resume_from_checkpoint, │
│ 1667 │ │ │ trial=trial, │
│ │
│ /usr/local/lib/python3.10/dist-packages/transformers/trainer.py:1909 in _inner_training_loop │
│ │
│ 1906 │ │ │ │ rng_to_sync = True │
│ 1907 │ │ │ │
│ 1908 │ │ │ step = -1 │
│ ❱ 1909 │ │ │ for step, inputs in enumerate(epoch_iterator): │
│ 1910 │ │ │ │ total_batched_samples += 1 │
│ 1911 │ │ │ │ if rng_to_sync: │
│ 1912 │ │ │ │ │ self._load_rng_state(resume_from_checkpoint) │
│ │
│ /usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:634 in __next__ │
│ │
│ 631 │ │ │ if self._sampler_iter is None: │
│ 632 │ │ │ │ # TODO(https://github.com/pytorch/pytorch/issues/76750) │
│ 633 │ │ │ │ self._reset() # type: ignore[call-arg] │
│ ❱ 634 │ │ │ data = self._next_data() │
│ 635 │ │ │ self._num_yielded += 1 │
│ 636 │ │ │ if self._dataset_kind == _DatasetKind.Iterable and \ │
│ 637 │ │ │ │ │ self._IterableDataset_len_called is not None and \ │
│ │
│ /usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:678 in _next_data │
│ │
│ 675 │ │
│ 676 │ def _next_data(self): │
│ 677 │ │ index = self._next_index() # may raise StopIteration │
│ ❱ 678 │ │ data = self._dataset_fetcher.fetch(index) # may raise StopIteration │
│ 679 │ │ if self._pin_memory: │
│ 680 │ │ │ data = _utils.pin_memory.pin_memory(data, self._pin_memory_device) │
│ 681 │ │ return data │
│ │
│ /usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py:49 in fetch │
│ │
│ 46 │ def fetch(self, possibly_batched_index): │
│ 47 │ │ if self.auto_collation: │
│ 48 │ │ │ if hasattr(self.dataset, "__getitems__") and self.dataset.__getitems__: │
│ ❱ 49 │ │ │ │ data = self.dataset.__getitems__(possibly_batched_index) │
│ 50 │ │ │ else: │
│ 51 │ │ │ │ data = [self.dataset[idx] for idx in possibly_batched_index] │
│ 52 │ │ else: │
│ │
│ /usr/local/lib/python3.10/dist-packages/datasets/arrow_dataset.py:2782 in __getitems__ │
│ │
│ 2779 │ │
│ 2780 │ def __getitems__(self, keys: List) -> List: │
│ 2781 │ │ """Can be used to get a batch using a list of integers indices.""" │
│ ❱ 2782 │ │ batch = self.__getitem__(keys) │
│ 2783 │ │ n_examples = len(batch[next(iter(batch))]) │
│ 2784 │ │ return [{col: array[i] for col, array in batch.items()} for i in range(n_example │
│ 2785 │
│ │
│ /usr/local/lib/python3.10/dist-packages/datasets/arrow_dataset.py:2778 in __getitem__ │
│ │
│ 2775 │ │
│ 2776 │ def __getitem__(self, key): # noqa: F811 │
│ 2777 │ │ """Can be used to index columns (by string names) or rows (by integer index or i │
│ ❱ 2778 │ │ return self._getitem(key) │
│ 2779 │ │
│ 2780 │ def __getitems__(self, keys: List) -> List: │
│ 2781 │ │ """Can be used to get a batch using a list of integers indices.""" │
│ │
│ /usr/local/lib/python3.10/dist-packages/datasets/arrow_dataset.py:2762 in _getitem │
│ │
│ 2759 │ │ format_kwargs = kwargs["format_kwargs"] if "format_kwargs" in kwargs else self._ │
│ 2760 │ │ format_kwargs = format_kwargs if format_kwargs is not None else {} │
│ 2761 │ │ formatter = get_formatter(format_type, features=self._info.features, **format_kw │
│ ❱ 2762 │ │ pa_subtable = query_table(self._data, key, indices=self._indices if self._indice │
│ 2763 │ │ formatted_output = format_table( │
│ 2764 │ │ │ pa_subtable, key, formatter=formatter, format_columns=format_columns, output │
│ 2765 │ │ ) │
│ │
│ /usr/local/lib/python3.10/dist-packages/datasets/formatting/formatting.py:578 in query_table │
│ │
│ 575 │ │ _check_valid_column_key(key, table.column_names) │
│ 576 │ else: │
│ 577 │ │ size = indices.num_rows if indices is not None else table.num_rows │
│ ❱ 578 │ │ _check_valid_index_key(key, size) │
│ 579 │ # Query the main table │
│ 580 │ if indices is None: │
│ 581 │ │ pa_subtable = _query_table(table, key) │
│ │
│ /usr/local/lib/python3.10/dist-packages/datasets/formatting/formatting.py:531 in │
│ _check_valid_index_key │
│ │
│ 528 │ │ │ _check_valid_index_key(min(key), size=size) │
│ 529 │ elif isinstance(key, Iterable): │
│ 530 │ │ if len(key) > 0: │
│ ❱ 531 │ │ │ _check_valid_index_key(int(max(key)), size=size) │
│ 532 │ │ │ _check_valid_index_key(int(min(key)), size=size) │
│ 533 │ else: │
│ 534 │ │ _raise_bad_key_type(key) │
│ │
│ /usr/local/lib/python3.10/dist-packages/datasets/formatting/formatting.py:521 in │
│ _check_valid_index_key │
│ │
│ 518 def _check_valid_index_key(key: Union[int, slice, range, Iterable], size: int) -> None: │
│ 519 │ if isinstance(key, int): │
│ 520 │ │ if (key < 0 and key + size < 0) or (key >= size): │
│ ❱ 521 │ │ │ raise IndexError(f"Invalid key: {key} is out of bounds for size {size}") │
│ 522 │ │ return │
│ 523 │ elif isinstance(key, slice): │
│ 524 │ │ pass │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
IndexError: Invalid key: 19 is out of bounds for size 0