maxmustermann/DeepLearningExamples
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

reflect default paths

Browse source 
Due to server issues with BookCorpus, the data download script skips downloading BookCorpus by default.
This commit is contained in:
Sharath TS 2021-03-09 16:23:55 -08:00 committed by GitHub
parent 8e131dd43b
commit dd6b8ca2bb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
PyTorch/LanguageModeling/BERT/scripts/run_pretraining.sh
View file

@ -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"}