Merge pull request #427 from jeonsworld/patch-1

fix sample_doc

examples/lm_finetuning/pregenerate_training_data.py

@@ -49,7 +49,7 @@ class DocumentDatabase:
                 self._precalculate_doc_weights()
             rand_start = self.doc_cumsum[current_idx]
             rand_end = rand_start + self.cumsum_max - self.doc_lengths[current_idx]
-            sentence_index = randint(rand_start, rand_end) % self.cumsum_max
+            sentence_index = randint(rand_start, rand_end-1) % self.cumsum_max
             sampled_doc_index = np.searchsorted(self.doc_cumsum, sentence_index, side='right')
         else:
             # If we don't use sentence weighting, then every doc has an equal chance to be chosen