代码拉取完成,页面将自动刷新
BERT-base SQuAD task Fine-tuning
cd <your_project_path>/nlp/querstion_answering/bert/pytorch
pip3 install -r requirements.txt
# Get "bert-base-uncased" from [Huggingface](https://huggingface.co/bert-base-uncased)
## Install lfs
wget https://packagecloud.io/github/git-lfs/packages/el/7/git-lfs-2.13.2-1.el7.x86_64.rpm/download -O lfs.rpm
rpm -ivh lfs.rpm
## Clone from Huggingface, it may take long time for large file
git lfs install
git clone https://huggingface.co/bert-base-uncased
Make sure you've got "bert-base-uncased" ready in ./bert-base-uncased
## config "dataset_name" to be local path of squad if you want to run off-line
## e.g. --dataset_name /path/to/squad
bash run.sh
## config "dataset_name" to be local path of squad if you want to run off-line
## e.g. --dataset_name /path/to/squad
bash run_dist.sh
GPUs | Samples/s | F1 |
---|---|---|
1x1 | 128.86 | 87 |
1x8 | 208.6 | 78.69 |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。