| 85 | self.logger.error(message, *args, **kwargs) |
| 86 | |
| 87 | def get_argument_parser(): |
| 88 | parser = argparse.ArgumentParser() |
| 89 | |
| 90 | # Required_parameter |
| 91 | parser.add_argument( |
| 92 | "--config-file", |
| 93 | "--cf", |
| 94 | help="pointer to the configuration file of the experiment", |
| 95 | type=str, |
| 96 | required=True) |
| 97 | parser.add_argument( |
| 98 | "--output_dir", |
| 99 | default=None, |
| 100 | type=str, |
| 101 | required=True, |
| 102 | help="The output directory where the model checkpoints will be written." |
| 103 | ) |
| 104 | |
| 105 | parser.add_argument( |
| 106 | "--token_nosing_prob", |
| 107 | default=0.15, |
| 108 | type=float, |
| 109 | help="The probability that a token is masked." |
| 110 | ) |
| 111 | |
| 112 | # Optional Params |
| 113 | parser.add_argument( |
| 114 | "--max_seq_length", |
| 115 | default=1024, |
| 116 | type=int, |
| 117 | help= |
| 118 | "The maximum total input sequence length after WordPiece tokenization. Sequences " |
| 119 | "longer than this will be truncated, and sequences shorter than this will be padded." |
| 120 | ) |
| 121 | parser.add_argument( |
| 122 | "--max_predictions_per_seq", |
| 123 | "--max_pred", |
| 124 | default=80, |
| 125 | type=int, |
| 126 | help= |
| 127 | "The maximum number of masked tokens in a sequence to be predicted.") |
| 128 | parser.add_argument('--seed', |
| 129 | type=int, |
| 130 | default=42, |
| 131 | help="random seed for initialization") |
| 132 | |
| 133 | parser.add_argument( |
| 134 | "--do_lower_case", |
| 135 | default=True, |
| 136 | action='store_true', |
| 137 | help= |
| 138 | "Whether to lower case the input text. True for uncased models, False for cased models." |
| 139 | ) |
| 140 | parser.add_argument("--local_rank", |
| 141 | type=int, |
| 142 | default=-1, |
| 143 | help="local_rank for distributed training on gpus") |
| 144 | |