资源算法BERT-Fine_tune

BERT-Fine_tune

2020-04-13 | |  76 |   0 |   0

Bert-Fine_tune

Install dependency

pip install -r requirements.txt

Train

python src/main.py --mode train --batch_size {batch_size} --learning_rate 1e-5 
                   --num_train_epochs 3 --data_name mb 
                   --eval_steps 1000 --data_path data --learning_rate 3e-5 
                   --num_train_epochs 3 --pytorch_dump_path saved/saved.{experiment_name} 
                   --output_path out.{experiment} --predict_path predict.{experiment}

Test

python src/main.py --mode test --batch_size {batch_size} --learning_rate 1e-5 
                   --num_train_epochs 3 --data_name robust04 
                   --eval_steps 1000 --data_path data --learning_rate 3e-5 
                   --num_train_epochs 3 --load_trained 
                   --pytorch_dump_path saved/saved.{experiment_name} 
                   --output_path out.{experiment} --predict_path predict.{experiment}


上一篇:BERT-chinese-text-classification-pytorch

下一篇:bert-sentence-similarity-pytorch

用户评价
全部评价

热门资源

  • TensorFlow-Course

    This repository aims to provide simple and read...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • mxnet_VanillaCNN

    This is a mxnet implementation of the Vanilla C...

  • DuReader_QANet_BiDAF

    Machine Reading Comprehension on DuReader Usin...

  • Klukshu-Sockeye-...

    KLUKSHU SOCKEYE PROJECTS 2016 This repositor...