def parse_args()

in luke/run_luke_ner_no_trainer.py [0:0]


def parse_args():
    parser = argparse.ArgumentParser(
        description="Finetune (m)LUKE on a token classification task (such as NER) with the accelerate library"
    )
    parser.add_argument(
        "--dataset_name",
        type=str,
        default=None,
        help="The name of the dataset to use (via the datasets library).",
    )
    parser.add_argument(
        "--dataset_config_name",
        type=str,
        default=None,
        help="The configuration name of the dataset to use (via the datasets library).",
    )
    parser.add_argument(
        "--train_file", type=str, default=None, help="A csv or a json file containing the training data."
    )
    parser.add_argument(
        "--validation_file", type=str, default=None, help="A csv or a json file containing the validation data."
    )
    parser.add_argument(
        "--text_column_name",
        type=str,
        default=None,
        help="The column name of text to input in the file (a csv or JSON file).",
    )
    parser.add_argument(
        "--label_column_name",
        type=str,
        default=None,
        help="The column name of label to input in the file (a csv or JSON file).",
    )
    parser.add_argument(
        "--max_length",
        type=int,
        default=128,
        help=(
            "The maximum total input sequence length after tokenization. Sequences longer than this will be truncated,"
            " sequences shorter will be padded if `--pad_to_max_length` is passed."
        ),
    )
    parser.add_argument(
        "--max_entity_length",
        type=int,
        default=32,
        help=(
            "The maximum total input entity length after tokenization (Used only for (M)Luke models). Sequences longer"
            " than this will be truncated, sequences shorter will be padded if `--pad_to_max_length` is passed."
        ),
    )
    parser.add_argument(
        "--max_mention_length",
        type=int,
        default=30,
        help=(
            "The maximum total input mention length after tokenization (Used only for (M)Luke models). Sequences"
            " longer than this will be truncated, sequences shorter will be padded if `--pad_to_max_length` is passed."
        ),
    )
    parser.add_argument(
        "--pad_to_max_length",
        action="store_true",
        help="If passed, pad all samples to `max_length`. Otherwise, dynamic padding is used.",
    )
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to pretrained model or model identifier from huggingface.co/models.",
        required=True,
    )
    parser.add_argument(
        "--config_name",
        type=str,
        default=None,
        help="Pretrained config name or path if not the same as model_name",
    )
    parser.add_argument(
        "--tokenizer_name",
        type=str,
        default=None,
        help="Pretrained tokenizer name or path if not the same as model_name",
    )
    parser.add_argument(
        "--per_device_train_batch_size",
        type=int,
        default=8,
        help="Batch size (per device) for the training dataloader.",
    )
    parser.add_argument(
        "--per_device_eval_batch_size",
        type=int,
        default=8,
        help="Batch size (per device) for the evaluation dataloader.",
    )
    parser.add_argument(
        "--learning_rate",
        type=float,
        default=5e-5,
        help="Initial learning rate (after the potential warmup period) to use.",
    )
    parser.add_argument("--weight_decay", type=float, default=0.0, help="Weight decay to use.")
    parser.add_argument("--num_train_epochs", type=int, default=3, help="Total number of training epochs to perform.")
    parser.add_argument(
        "--max_train_steps",
        type=int,
        default=None,
        help="Total number of training steps to perform. If provided, overrides num_train_epochs.",
    )
    parser.add_argument(
        "--gradient_accumulation_steps",
        type=int,
        default=1,
        help="Number of updates steps to accumulate before performing a backward/update pass.",
    )
    parser.add_argument(
        "--lr_scheduler_type",
        type=SchedulerType,
        default="linear",
        help="The scheduler type to use.",
        choices=["linear", "cosine", "cosine_with_restarts", "polynomial", "constant", "constant_with_warmup"],
    )
    parser.add_argument(
        "--num_warmup_steps", type=int, default=0, help="Number of steps for the warmup in the lr scheduler."
    )
    parser.add_argument("--output_dir", type=str, default=None, help="Where to store the final model.")
    parser.add_argument("--seed", type=int, default=None, help="A seed for reproducible training.")
    parser.add_argument(
        "--label_all_tokens",
        action="store_true",
        help="Setting labels of all special tokens to -100 and thus PyTorch will ignore them.",
    )
    parser.add_argument(
        "--return_entity_level_metrics",
        action="store_true",
        help="Indication whether entity level metrics are to be returner.",
    )
    parser.add_argument(
        "--task_name",
        type=str,
        default="ner",
        choices=["ner", "pos", "chunk"],
        help="The name of the task.",
    )
    parser.add_argument(
        "--debug",
        action="store_true",
        help="Activate debug mode and run training only with a subset of data.",
    )
    parser.add_argument("--push_to_hub", action="store_true", help="Whether or not to push the model to the Hub.")
    parser.add_argument(
        "--hub_model_id", type=str, help="The name of the repository to keep in sync with the local `output_dir`."
    )
    parser.add_argument("--hub_token", type=str, help="The token to use to push to the Model Hub.")
    args = parser.parse_args()

    # Sanity checks
    if args.task_name is None and args.train_file is None and args.validation_file is None:
        raise ValueError("Need either a task name or a training/validation file.")
    else:
        if args.train_file is not None:
            extension = args.train_file.split(".")[-1]
            assert extension in ["csv", "json"], "`train_file` should be a csv or a json file."
        if args.validation_file is not None:
            extension = args.validation_file.split(".")[-1]
            assert extension in ["csv", "json"], "`validation_file` should be a csv or a json file."

    if args.push_to_hub:
        assert args.output_dir is not None, "Need an `output_dir` to create a repo when `--push_to_hub` is passed."

    return args