rag-end2end-retriever/lightning_base.py [174:227]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.dataset_size = len(self.test_dataloader().dataset)
        else:
            self.train_loader = self.get_dataloader("train", self.hparams.train_batch_size, shuffle=True)
            self.dataset_size = len(self.train_dataloader().dataset)

    def get_dataloader(self, type_path: str, batch_size: int, shuffle: bool = False):
        raise NotImplementedError("You must implement this for your task")

    def train_dataloader(self):
        return self.train_loader

    def val_dataloader(self):
        return self.get_dataloader("dev", self.hparams.eval_batch_size, shuffle=False)

    def test_dataloader(self):
        return self.get_dataloader("test", self.hparams.eval_batch_size, shuffle=False)

    def _feature_file(self, mode):
        return os.path.join(
            self.hparams.data_dir,
            "cached_{}_{}_{}".format(
                mode,
                list(filter(None, self.hparams.model_name_or_path.split("/"))).pop(),
                str(self.hparams.max_seq_length),
            ),
        )

    @pl.utilities.rank_zero_only
    def on_save_checkpoint(self, checkpoint: Dict[str, Any]) -> None:
        save_path = self.output_dir.joinpath("best_tfmr")
        self.model.config.save_step = self.step_count
        self.model.save_pretrained(save_path)
        self.tokenizer.save_pretrained(save_path)

    @staticmethod
    def add_model_specific_args(parser, root_dir):
        parser.add_argument(
            "--model_name_or_path",
            default=None,
            type=str,
            required=True,
            help="Path to pretrained model or model identifier from huggingface.co/models",
        )
        parser.add_argument(
            "--config_name", default="", type=str, help="Pretrained config name or path if not the same as model_name"
        )
        parser.add_argument(
            "--tokenizer_name",
            default=None,
            type=str,
            help="Pretrained tokenizer name or path if not the same as model_name",
        )
        parser.add_argument(
            "--cache_dir",
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



seq2seq-distillation/lightning_base.py [172:225]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.dataset_size = len(self.test_dataloader().dataset)
        else:
            self.train_loader = self.get_dataloader("train", self.hparams.train_batch_size, shuffle=True)
            self.dataset_size = len(self.train_dataloader().dataset)

    def get_dataloader(self, type_path: str, batch_size: int, shuffle: bool = False):
        raise NotImplementedError("You must implement this for your task")

    def train_dataloader(self):
        return self.train_loader

    def val_dataloader(self):
        return self.get_dataloader("dev", self.hparams.eval_batch_size, shuffle=False)

    def test_dataloader(self):
        return self.get_dataloader("test", self.hparams.eval_batch_size, shuffle=False)

    def _feature_file(self, mode):
        return os.path.join(
            self.hparams.data_dir,
            "cached_{}_{}_{}".format(
                mode,
                list(filter(None, self.hparams.model_name_or_path.split("/"))).pop(),
                str(self.hparams.max_seq_length),
            ),
        )

    @pl.utilities.rank_zero_only
    def on_save_checkpoint(self, checkpoint: Dict[str, Any]) -> None:
        save_path = self.output_dir.joinpath("best_tfmr")
        self.model.config.save_step = self.step_count
        self.model.save_pretrained(save_path)
        self.tokenizer.save_pretrained(save_path)

    @staticmethod
    def add_model_specific_args(parser, root_dir):
        parser.add_argument(
            "--model_name_or_path",
            default=None,
            type=str,
            required=True,
            help="Path to pretrained model or model identifier from huggingface.co/models",
        )
        parser.add_argument(
            "--config_name", default="", type=str, help="Pretrained config name or path if not the same as model_name"
        )
        parser.add_argument(
            "--tokenizer_name",
            default=None,
            type=str,
            help="Pretrained tokenizer name or path if not the same as model_name",
        )
        parser.add_argument(
            "--cache_dir",
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -