Error in Kaggle Orpheus_(3B)-TTS finetune notebook

[karim23657]

@Erland366 @Etherll , Hi , I used Orpheus_(3B) Kaggle notebook and when i executed cell trainer_stats = trainer.train() it returns this error :

ValueError                                Traceback (most recent call last)
<ipython-input-8-3d62c575fcfd> in <cell line: 1>()
----> 1 trainer_stats = trainer.train()

/usr/local/lib/python3.10/dist-packages/transformers/trainer.py in train(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)
   2243                 hf_hub_utils.enable_progress_bars()
   2244         else:
-> 2245             return inner_training_loop(
   2246                 args=args,
   2247                 resume_from_checkpoint=resume_from_checkpoint,

/usr/local/lib/python3.10/dist-packages/unsloth/models/llama.py in _fast_inner_training_loop(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)

/usr/local/lib/python3.10/dist-packages/unsloth_zoo/loss_utils.py in _unsloth_get_batch_samples(self, epoch_iterator, num_batches, device, *args, **kwargs)
    269     for _ in range(num_batches):
    270         try:
--> 271             batch_samples += [next(epoch_iterator)]
    272         except StopIteration:
    273             break

/usr/local/lib/python3.10/dist-packages/accelerate/data_loader.py in __iter__(self)
    550         # We iterate one batch ahead to check when we are at the end
    551         try:
--> 552             current_batch = next(dataloader_iter)
    553         except StopIteration:
    554             yield

/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py in __next__(self)
    699                 # TODO(https://github.com/pytorch/pytorch/issues/76750)
    700                 self._reset()  # type: ignore[call-arg]
--> 701             data = self._next_data()
    702             self._num_yielded += 1
    703             if (

/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py in _next_data(self)
    755     def _next_data(self):
    756         index = self._next_index()  # may raise StopIteration
--> 757         data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
    758         if self._pin_memory:
    759             data = _utils.pin_memory.pin_memory(data, self._pin_memory_device)

/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py in fetch(self, possibly_batched_index)
     53         else:
     54             data = self.dataset[possibly_batched_index]
---> 55         return self.collate_fn(data)

/usr/local/lib/python3.10/dist-packages/transformers/data/data_collator.py in default_data_collator(features, return_tensors)
     91 
     92     if return_tensors == "pt":
---> 93         return torch_default_data_collator(features)
     94     elif return_tensors == "tf":
     95         return tf_default_data_collator(features)

/usr/local/lib/python3.10/dist-packages/transformers/data/data_collator.py in torch_default_data_collator(features)
    157                 batch[k] = torch.from_numpy(np.stack([f[k] for f in features]))
    158             else:
--> 159                 batch[k] = torch.tensor([f[k] for f in features])
    160 
    161     return batch

ValueError: expected sequence of length 715 at dim 1 (got 614)

[rupaut98]

You can checkout my pull request for the solution: #27