def get_eval_dataloader()

in trl/trainer/online_dpo_trainer.py [0:0]

• 36 lines of code
• 12 McCabe index (conditional complexity)

    def get_eval_dataloader(self, eval_dataset: Optional[Union[str, Dataset]] = None) -> DataLoader:
        if eval_dataset is None and self.eval_dataset is None:
            raise ValueError("Trainer: evaluation requires an eval_dataset.")

        # If we have persistent workers, don't do a fork bomb especially as eval datasets
        # don't change during training
        dataloader_key = eval_dataset if isinstance(eval_dataset, str) else "eval"
        if (
            hasattr(self, "_eval_dataloaders")
            and dataloader_key in self._eval_dataloaders
            and self.args.dataloader_persistent_workers
        ):
            return self.accelerator.prepare(self._eval_dataloaders[dataloader_key])

        eval_dataset = (
            self.eval_dataset[eval_dataset]
            if isinstance(eval_dataset, str)
            else eval_dataset
            if eval_dataset is not None
            else self.eval_dataset
        )
        data_collator = self.data_collator

        dataloader_params = {
            "batch_size": self.args.eval_batch_size,
            "collate_fn": data_collator,
            "num_workers": self.args.dataloader_num_workers,
            "pin_memory": self.args.dataloader_pin_memory,
            "persistent_workers": self.args.dataloader_persistent_workers,
        }

        if not isinstance(eval_dataset, torch.utils.data.IterableDataset):
            dataloader_params["sampler"] = self._get_eval_sampler(eval_dataset)
            dataloader_params["drop_last"] = self.args.dataloader_drop_last
            dataloader_params["prefetch_factor"] = self.args.dataloader_prefetch_factor

        # accelerator.free_memory() will destroy the references, so
        # we need to store the non-prepared version
        eval_dataloader = DataLoader(eval_dataset, **dataloader_params)
        if self.args.dataloader_persistent_workers:
            if hasattr(self, "_eval_dataloaders"):
                self._eval_dataloaders[dataloader_key] = eval_dataloader
            else:
                self._eval_dataloaders = {dataloader_key: eval_dataloader}

        return self.accelerator.prepare(eval_dataloader)