reflect default paths

Due to server issues with BookCorpus, the data download script skips downloading BookCorpus by default.

PyTorch/LanguageModeling/BERT/scripts/run_pretraining.sh

@@ -34,10 +34,10 @@ learning_rate_phase2=${17:-"4e-3"}
 warmup_proportion_phase2=${18:-"0.128"}
 train_steps_phase2=${19:-1563}
 gradient_accumulation_steps_phase2=${20:-512}
-DATASET=hdf5_lower_case_1_seq_len_128_max_pred_20_masked_lm_prob_0.15_random_seed_12345_dupe_factor_5/books_wiki_en_corpus # change this for other datasets
+DATASET=hdf5_lower_case_1_seq_len_128_max_pred_20_masked_lm_prob_0.15_random_seed_12345_dupe_factor_5/wikicorpus_en # change this for other datasets
 DATA_DIR_PHASE1=${21:-$BERT_PREP_WORKING_DIR/${DATASET}/}
 BERT_CONFIG=bert_config.json
-DATASET2=hdf5_lower_case_1_seq_len_512_max_pred_80_masked_lm_prob_0.15_random_seed_12345_dupe_factor_5/books_wiki_en_corpus # change this for other datasets
+DATASET2=hdf5_lower_case_1_seq_len_512_max_pred_80_masked_lm_prob_0.15_random_seed_12345_dupe_factor_5/wikicorpus_en # change this for other datasets
 DATA_DIR_PHASE2=${22:-$BERT_PREP_WORKING_DIR/${DATASET2}/}
 CODEDIR=${23:-"/workspace/bert"}
 init_checkpoint=${24:-"None"}