remove default when action is store_true in arguments

examples/extract_features.py

@@ -199,7 +199,7 @@ def main():
                              "bert-large-uncased, bert-base-cased, bert-base-multilingual, bert-base-chinese.")
 
     ## Other parameters
-    parser.add_argument("--do_lower_case", default=False, action='store_true', help="Set this flag if you are using an uncased model.")
+    parser.add_argument("--do_lower_case", action='store_true', help="Set this flag if you are using an uncased model.")
     parser.add_argument("--layers", default="-1,-2,-3,-4", type=str)
     parser.add_argument("--max_seq_length", default=128, type=int,
                         help="The maximum total input sequence length after WordPiece tokenization. Sequences longer "
@@ -210,7 +210,6 @@ def main():
                         default=-1,
                         help = "local_rank for distributed training on gpus")
     parser.add_argument("--no_cuda",
-                        default=False,
                         action='store_true',
                         help="Whether not to use CUDA when available")
 

examples/run_classifier.py

@@ -333,15 +333,12 @@ def main():
                              "Sequences longer than this will be truncated, and sequences shorter \n"
                              "than this will be padded.")
     parser.add_argument("--do_train",
-                        default=False,
                         action='store_true',
                         help="Whether to run training.")
     parser.add_argument("--do_eval",
-                        default=False,
                         action='store_true',
                         help="Whether to run eval on the dev set.")
     parser.add_argument("--do_lower_case",
-                        default=False,
                         action='store_true',
                         help="Set this flag if you are using an uncased model.")
     parser.add_argument("--train_batch_size",
@@ -366,7 +363,6 @@ def main():
                         help="Proportion of training to perform linear learning rate warmup for. "
                              "E.g., 0.1 = 10%% of training.")
     parser.add_argument("--no_cuda",
-                        default=False,
                         action='store_true',
                         help="Whether not to use CUDA when available")
     parser.add_argument("--local_rank",
@@ -382,7 +378,6 @@ def main():
                         default=1,
                         help="Number of updates steps to accumulate before performing a backward/update pass.")
     parser.add_argument('--fp16',
-                        default=False,
                         action='store_true',
                         help="Whether to use 16-bit float precision instead of 32-bit")
     parser.add_argument('--loss_scale',

examples/run_lm_finetuning.py

@@ -432,7 +432,6 @@ def main():
                              "Sequences longer than this will be truncated, and sequences shorter \n"
                              "than this will be padded.")
     parser.add_argument("--do_train",
-                        default=False,
                         action='store_true',
                         help="Whether to run training.")
     parser.add_argument("--train_batch_size",
@@ -457,11 +456,9 @@ def main():
                         help="Proportion of training to perform linear learning rate warmup for. "
                              "E.g., 0.1 = 10%% of training.")
     parser.add_argument("--no_cuda",
-                        default=False,
                         action='store_true',
                         help="Whether not to use CUDA when available")
     parser.add_argument("--on_memory",
-                        default=False,
                         action='store_true',
                         help="Whether to load train samples into memory or use disk")
     parser.add_argument("--local_rank",
@@ -477,7 +474,6 @@ def main():
                         default=1,
                         help="Number of updates steps to accumualte before performing a backward/update pass.")
     parser.add_argument('--fp16',
-                        default=False,
                         action='store_true',
                         help="Whether to use 16-bit float precision instead of 32-bit")
     parser.add_argument('--loss_scale',

examples/run_squad.py

@@ -698,8 +698,8 @@ def main():
     parser.add_argument("--max_query_length", default=64, type=int,
                         help="The maximum number of tokens for the question. Questions longer than this will "
                              "be truncated to this length.")
-    parser.add_argument("--do_train", default=False, action='store_true', help="Whether to run training.")
-    parser.add_argument("--do_predict", default=False, action='store_true', help="Whether to run eval on the dev set.")
+    parser.add_argument("--do_train", action='store_true', help="Whether to run training.")
+    parser.add_argument("--do_predict", action='store_true', help="Whether to run eval on the dev set.")
     parser.add_argument("--train_batch_size", default=32, type=int, help="Total batch size for training.")
     parser.add_argument("--predict_batch_size", default=8, type=int, help="Total batch size for predictions.")
     parser.add_argument("--learning_rate", default=5e-5, type=float, help="The initial learning rate for Adam.")
@@ -714,11 +714,10 @@ def main():
     parser.add_argument("--max_answer_length", default=30, type=int,
                         help="The maximum length of an answer that can be generated. This is needed because the start "
                              "and end predictions are not conditioned on one another.")
-    parser.add_argument("--verbose_logging", default=False, action='store_true',
+    parser.add_argument("--verbose_logging", action='store_true',
                         help="If true, all of the warnings related to data processing will be printed. "
                              "A number of warnings are expected for a normal SQuAD evaluation.")
     parser.add_argument("--no_cuda",
-                        default=False,
                         action='store_true',
                         help="Whether not to use CUDA when available")
     parser.add_argument('--seed',
@@ -730,7 +729,6 @@ def main():
                         default=1,
                         help="Number of updates steps to accumulate before performing a backward/update pass.")
     parser.add_argument("--do_lower_case",
-                        default=True,
                         action='store_true',
                         help="Whether to lower case the input text. True for uncased models, False for cased models.")
     parser.add_argument("--local_rank",
@@ -738,7 +736,6 @@ def main():
                         default=-1,
                         help="local_rank for distributed training on gpus")
     parser.add_argument('--fp16',
-                        default=False,
                         action='store_true',
                         help="Whether to use 16-bit float precision instead of 32-bit")
     parser.add_argument('--loss_scale',

examples/run_swag.py

@@ -265,15 +265,12 @@ def main():
                              "Sequences longer than this will be truncated, and sequences shorter \n"
                              "than this will be padded.")
     parser.add_argument("--do_train",
-                        default=False,
                         action='store_true',
                         help="Whether to run training.")
     parser.add_argument("--do_eval",
-                        default=False,
                         action='store_true',
                         help="Whether to run eval on the dev set.")
     parser.add_argument("--do_lower_case",
-                        default=False,
                         action='store_true',
                         help="Set this flag if you are using an uncased model.")
     parser.add_argument("--train_batch_size",
@@ -298,7 +295,6 @@ def main():
                         help="Proportion of training to perform linear learning rate warmup for. "
                              "E.g., 0.1 = 10%% of training.")
     parser.add_argument("--no_cuda",
-                        default=False,
                         action='store_true',
                         help="Whether not to use CUDA when available")
     parser.add_argument("--local_rank",
@@ -314,7 +310,6 @@ def main():
                         default=1,
                         help="Number of updates steps to accumulate before performing a backward/update pass.")
     parser.add_argument('--fp16',
-                        default=False,
                         action='store_true',
                         help="Whether to use 16-bit float precision instead of 32-bit")
     parser.add_argument('--loss_scale',