From 289cf4d2b7cf090942e2e7dc4e6134a81095adf6 Mon Sep 17 00:00:00 2001
From: VictorSanh <victorsanh@gmail.com>
Date: Tue, 5 Nov 2019 10:10:02 -0500
Subject: [PATCH] change default for XNLI: dev --> test

---
 examples/run_xnli.py   | 6 +++---
 examples/utils_xnli.py | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/examples/run_xnli.py b/examples/run_xnli.py
index a9b2e46c13..7fbbf7d152 100644
--- a/examples/run_xnli.py
+++ b/examples/run_xnli.py
@@ -270,7 +270,7 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
     output_mode = output_modes[task]
     # Load data features from cache or dataset file
     cached_features_file = os.path.join(args.data_dir, 'cached_{}_{}_{}_{}_{}'.format(
-        'dev' if evaluate else 'train',
+        'test' if evaluate else 'train',
         list(filter(None, args.model_name_or_path.split('/'))).pop(),
         str(args.max_seq_length),
         str(task),
@@ -281,7 +281,7 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
     else:
         logger.info("Creating features from dataset file at %s", args.data_dir)
         label_list = processor.get_labels()
-        examples = processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir)
+        examples = processor.get_test_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir)
         features = convert_examples_to_features(examples,
                                                 tokenizer,
                                                 label_list=label_list,
@@ -341,7 +341,7 @@ def main():
     parser.add_argument("--do_train", action='store_true',
                         help="Whether to run training.")
     parser.add_argument("--do_eval", action='store_true',
-                        help="Whether to run eval on the dev set.")
+                        help="Whether to run eval on the test set.")
     parser.add_argument("--evaluate_during_training", action='store_true',
                         help="Rul evaluation during training at each logging step.")
     parser.add_argument("--do_lower_case", action='store_true',
diff --git a/examples/utils_xnli.py b/examples/utils_xnli.py
index f0238f4664..482e79a81f 100644
--- a/examples/utils_xnli.py
+++ b/examples/utils_xnli.py
@@ -50,9 +50,9 @@ class XnliProcessor(DataProcessor):
                 InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
         return examples
 
-    def get_dev_examples(self, data_dir):
+    def get_test_examples(self, data_dir):
         """See base class."""
-        lines = self._read_tsv(os.path.join(data_dir, "XNLI-1.0/xnli.dev.tsv"))
+        lines = self._read_tsv(os.path.join(data_dir, "XNLI-1.0/xnli.test.tsv"))
         examples = []
         for (i, line) in enumerate(lines):
             if i == 0:
@@ -60,7 +60,7 @@ class XnliProcessor(DataProcessor):
             language = line[0]
             if language != self.language:
                 continue
-            guid = "%s-%s" % ('dev', i)
+            guid = "%s-%s" % ('test', i)
             text_a = line[6]
             text_b = line[7]
             label = line[1]