clean up

run_classifier.py

@@ -192,8 +192,7 @@ class ColaProcessor(DataProcessor):
         return examples
 
 
-def convert_examples_to_features(examples, label_list, max_seq_length,
-                                                                 tokenizer):
+def convert_examples_to_features(examples, label_list, max_seq_length, tokenizer):
     """Loads a data file into a list of `InputBatch`s."""
 
     label_map = {}
@@ -380,7 +379,7 @@ def main():
     parser.add_argument("--do_lower_case",
                         default=False,
                         action='store_true',
-                        help="Whether to lower case the input text. Should be True for uncased models and False for cased models.")
+                        help="Whether to lower case the input text. True for uncased models, False for cased models.")
     parser.add_argument("--max_seq_length",
                         default=128,
                         type=int,
@@ -424,6 +423,10 @@ def main():
                         default=False,
                         action='store_true',
                         help="Whether not to use CUDA when available")
+    parser.add_argument("--accumulate_gradients",
+                        type=int,
+                        default=1,
+                        help="Number of steps to accumulate gradient on (divide the single step batch_size)")
     parser.add_argument("--local_rank",
                         type=int,
                         default=-1,

run_squad.py

@@ -18,15 +18,15 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
-import six
 import argparse
 import collections
 import logging
 import json
 import math
 import os
-from tqdm import tqdm, trange
+import six
 import random
+from tqdm import tqdm, trange
 
 import numpy as np
 import torch