def get_args()

in anli/src/nli/training.py [0:0]

• 141 lines of code
• 1 McCabe index (conditional complexity)

def get_args():
    parser = argparse.ArgumentParser()
    parser.add_argument("--cpu", action="store_true", help="If set, we only use CPU.")
    parser.add_argument(
        "--single_gpu", action="store_true", help="If set, we only use single GPU."
    )
    parser.add_argument("--fp16", action="store_true", help="If set, we will use fp16.")

    parser.add_argument(
        "--fp16_opt_level",
        type=str,
        default="O1",
        help="For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']."
        "See details at https://nvidia.github.io/apex/amp.html",
    )

    # environment arguments
    parser.add_argument(
        "-s", "--seed", default=1, type=int, metavar="N", help="manual random seed"
    )
    parser.add_argument(
        "-n", "--num_nodes", default=1, type=int, metavar="N", help="number of nodes"
    )
    parser.add_argument(
        "-g", "--gpus_per_node", default=1, type=int, help="number of gpus per node"
    )
    parser.add_argument(
        "-nr", "--node_rank", default=0, type=int, help="ranking within the nodes"
    )

    # experiments specific arguments
    parser.add_argument(
        "--debug_mode",
        action="store_true",
        dest="debug_mode",
        help="weather this is debug mode or normal",
    )

    parser.add_argument(
        "--model_class_name", type=str, help="Set the model class of the experiment.",
    )

    parser.add_argument(
        "--experiment_name",
        type=str,
        help="Set the name of the experiment. [model_name]/[data]/[task]/[other]",
    )

    parser.add_argument(
        "--save_prediction",
        action="store_true",
        dest="save_prediction",
        help="Do we want to save prediction",
    )

    parser.add_argument(
        "--epochs",
        default=2,
        type=int,
        metavar="N",
        help="number of total epochs to run",
    )
    parser.add_argument(
        "--per_gpu_train_batch_size",
        default=16,
        type=int,
        help="Batch size per GPU/CPU for training.",
    )
    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(
        "--per_gpu_eval_batch_size",
        default=64,
        type=int,
        help="Batch size per GPU/CPU for evaluation.",
    )

    parser.add_argument(
        "--max_length", default=160, type=int, help="Max length of the sequences."
    )

    parser.add_argument(
        "--warmup_steps", default=-1, type=int, help="Linear warmup over warmup_steps."
    )
    parser.add_argument(
        "--max_grad_norm", default=1.0, type=float, help="Max gradient norm."
    )
    parser.add_argument(
        "--learning_rate",
        default=1e-5,
        type=float,
        help="The initial learning rate for Adam.",
    )
    parser.add_argument(
        "--weight_decay", default=0.0, type=float, help="Weight decay if we apply some."
    )
    parser.add_argument(
        "--adam_epsilon", default=1e-8, type=float, help="Epsilon for Adam optimizer."
    )

    parser.add_argument(
        "--eval_frequency",
        default=1000,
        type=int,
        help="set the evaluation frequency, evaluate every X global step.",
    )

    parser.add_argument(
        "--train_data", type=str, help="The training data used in the experiments."
    )

    parser.add_argument(
        "--train_weights",
        type=str,
        help="The training data weights used in the experiments.",
    )

    parser.add_argument(
        "--eval_data", type=str, help="The training data used in the experiments."
    )

    parser.add_argument(
        "--flip_sent",
        default=False,
        action="store_true",
        help="Flip the hypothesis and premise",
    )

    parser.add_argument(
        "--train_from_scratch",
        default=False,
        action="store_true",
        help="Train model without using the pretrained weights",
    )

    parser.add_argument(
        "--train_with_lm",
        default=False,
        action="store_true",
        help="Train model with LM",
    )

    parser.add_argument(
        "--add_lm",
        default=False,
        action="store_true",
        help="Train model with LM add loss",
    )

    parser.add_argument(
        "--lm_lambda", default=0.1, type=float, help="lambda to train LM loss",
    )

    parser.add_argument("--skip_model_save", default=False, action="store_true")
    parser.add_argument("--save_on_wandb", default=False, action="store_true")

    # parser.add_argument("--local_rank", default=0, type=int)

    parser.add_argument("--slurm", default=False, action="store_true")

    args = parser.parse_args()
    return args