blink/common/params.py [207:235]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            help="Interval for evaluation during training",
        )
        parser.add_argument(
            "--save_interval", type=int, default=1, 
            help="Interval for model saving"
        )
        parser.add_argument(
            "--warmup_proportion",
            default=0.1,
            type=float,
            help="Proportion of training to perform linear learning rate warmup for. "
            "E.g., 0.1 = 10% of training.",
        )
        parser.add_argument(
            "--gradient_accumulation_steps",
            type=int,
            default=1,
            help="Number of updates steps to accumualte before performing a backward/update pass.",
        )
        parser.add_argument(
            "--type_optimization",
            type=str,
            default="all_encoder_layers",
            help="Which type of layers to optimize in BERT",
        )
        parser.add_argument(
            "--shuffle", type=bool, default=False, 
            help="Whether to shuffle train data",
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



elq/common/params.py [240:268]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            help="Interval for evaluation during training",
        )
        parser.add_argument(
            "--save_interval", type=int, default=1, 
            help="Interval for model saving"
        )
        parser.add_argument(
            "--warmup_proportion",
            default=0.1,
            type=float,
            help="Proportion of training to perform linear learning rate warmup for. "
            "E.g., 0.1 = 10% of training.",
        )
        parser.add_argument(
            "--gradient_accumulation_steps",
            type=int,
            default=1,
            help="Number of updates steps to accumualte before performing a backward/update pass.",
        )
        parser.add_argument(
            "--type_optimization",
            type=str,
            default="all_encoder_layers",
            help="Which type of layers to optimize in BERT",
        )
        parser.add_argument(
            "--shuffle", type=bool, default=False, 
            help="Whether to shuffle train data",
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -