Merge pull request #65 from imcaspar/dev

add Stale, Resolves #46

.github/stale.yml

@@ -0,0 +1,17 @@
+# Number of days of inactivity before an issue becomes stale
+daysUntilStale: 365
+# Number of days of inactivity before a stale issue is closed
+daysUntilClose: 30
+# Issues with these labels will never be considered stale
+exemptLabels:
+  - pinned
+  - security
+# Label to use when marking an issue as stale
+staleLabel: wontfix
+# Comment to post when marking an issue as stale. Set to `false` to disable
+markComment: >
+  This issue has been automatically marked as stale because it has not had
+  recent activity. It will be closed if no further activity occurs. Thank you
+  for your contributions.
+# Comment to post when closing a stale issue. Set to `false` to disable
+closeComment: true

dataset/prepare_data.py

@@ -185,7 +185,7 @@ def buffered_and_sliding_window_article_iterator(tokenizer, final_desired_size=1
 train_file = args.base_fn + 'train_wiki19_{:04d}.tfrecord'.format(args.fold)
 with S3TFRecordWriter(train_file) as train_writer:
     for article in buffered_and_sliding_window_article_iterator(tokenizer,
-                                                                final_desired_size=max(args.max_seq_length + 1, 1025)):
+                                                                final_desired_size=args.max_seq_length + 1):
         writer2use = train_writer
         assert len(article['input_ids']) == (args.max_seq_length + 1)