Method get_train_dataloader

src/transformers/trainer.py:871–889

Returns the training [`~torch.utils.data.DataLoader`]. Will use no sampler if `train_dataset` does not implement `__len__`, a random sampler (adapted to distributed training if necessary) otherwise. Subclass and override this method if you want to inject some custo

(self)

    # ---- Data Loading ----

    def get_train_dataloader(self) -> DataLoader:
        """
        Returns the training [`~torch.utils.data.DataLoader`].

        Will use no sampler if `train_dataset` does not implement `__len__`, a random sampler (adapted to distributed
        training if necessary) otherwise.

        Subclass and override this method if you want to inject some custom behavior.
        """
        if self.train_dataset is None:
            raise ValueError("Trainer: training requires a train_dataset.")

        return self._get_dataloader(
            dataset=self.train_dataset,
            description="Training",
            batch_size=self._train_batch_size,
            sampler_fn=self._get_train_sampler,
            is_training=True,
        )

    def get_eval_dataloader(self, eval_dataset: str | Dataset | None = None) -> DataLoader:
        """