language
language copied to clipboard
Fine Tune Script ReadMe Description Error
There is an error in the script for fine tuning the bert baseline:
--train_precomputed=nq-train.tfrecords-00000-of-00001 \
should be
--train_precomputed_file=bert-joint-baseline/nq-train.tfrecords-00000-of-00001 \
python -m language.question_answering.bert_joint.run_nq \
--logtostderr \
--bert_config_file=bert-joint-baseline/bert_config.json \
--vocab_file=bert-joint-baseline/vocab-nq.txt \
--train_precomputed_file=bert-joint-baseline/nq-train.tfrecords-00000-of-00001 \
--train_num_precomputed=494670 \
--learning_rate=3e-5 \
--num_train_epochs=1 \
--max_seq_length=512 \
--save_checkpoints_steps=5000 \
--init_checkpoint=uncased_L-24_H-1024_A-16/bert_model.ckpt \
--do_train \
--output_dir=bert_model_output
Same error occurred with me. I struggled with code only to realize this silly mistake.
Where can I find uncased_L-24_H-1024_A-16/bert_model.ckpt?
Where can I find uncased_L-24_H-1024_A-16/bert_model.ckpt?
https://storage.googleapis.com/bert_models/2019_05_30/wwm_uncased_L-24_H-1024_A-16.zip
Thanks!