training/flax/run_finetuning.py [211:238]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        metadata={"help": "Truncate transcriptions that are longer `max_label_length` tokens."},
    )
    pad_target_to_multiple_of: Optional[int] = field(
        default=None,
        metadata={
            "help": (
                "If set will pad the target sequence to a multiple of the provided"
                " value. This is important to avoid triggering recompilations on TPU."
                " If unspecified, will default to padding the targets to max length."
            )
        },
    )
    preprocessing_only: bool = field(
        default=False,
        metadata={
            "help": (
                "Whether to only do data preprocessing and skip training. This is"
                " especially useful when data preprocessing errors out in distributed"
                " training due to timeout. In this case, one should run the"
                " preprocessing in a non-distributed setup with"
                " `preprocessing_only=True` so that the cached datasets can"
                " consequently be loaded in distributed training"
            )
        },
    )
    train_split_name: str = field(
        default="train",
        metadata={
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/run_distillation.py [251:278]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        metadata={"help": "Truncate transcriptions that are longer `max_label_length` tokens."},
    )
    pad_target_to_multiple_of: Optional[int] = field(
        default=None,
        metadata={
            "help": (
                "If set will pad the target sequence to a multiple of the provided"
                " value. This is important to avoid triggering recompilations on TPU."
                " If unspecified, will default to padding the targets to max length."
            )
        },
    )
    preprocessing_only: bool = field(
        default=False,
        metadata={
            "help": (
                "Whether to only do data preprocessing and skip training. This is"
                " especially useful when data preprocessing errors out in distributed"
                " training due to timeout. In this case, one should run the"
                " preprocessing in a non-distributed setup with"
                " `preprocessing_only=True` so that the cached datasets can"
                " consequently be loaded in distributed training"
            )
        },
    )
    train_split_name: str = field(
        default="train",
        metadata={
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -