INNER CODE UNIT · Python

default

IBM/transition-amr-parser · src/ibm_neural_aligner/main.py:148

        default=2e-3,
        type=float,
    )
    parser.add_argument(
        "--batch-size",
        help="Batch size.",
        default=4,
        type=int,
    )
    parser.add_argument(
        "--accum-steps",
        help="Gradient accumulation steps.",
        default=1,
        type=int,
    )
    parser.add_argument(
        "--seed",
        help="Random seed.",

View source record →