This repository contains finetuning code and checkpoints for ElasticBERT.

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline

Xiangyang Liu, Tianxiang Sun, Junliang He, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

We recommend using Anaconda for setting up the environment of experiments:

conda create -n elasticbert python=3.8.8
conda activate elasticbert
conda install pytorch==1.8.1 cudatoolkit=11.1 -c pytorch -c conda-forge
pip install -r requirements.txt

We provide the pre-trained weights of ElasticBERT-BASE and ElasticBERT-LARGE, which can be directly used in Huggingface-Transformers.

• ElasticBERT-BASE: 12 layers, 12 Heads and 768 Hidden Size.
• ElasticBERT-LARGE: 24 layers, 16 Heads and 1024 Hidden Size.
• ElasticBERT-Chinese-BASE: ElasticBERT-Chinese has been uploaded to huggingface model hub. Welcome to download and use it.

The pre-trained weights can be downloaded here.

The GLUE task datasets can be downloaded from the GLUE leaderboard

The ELUE task datasets can be downloaded from the ELUE leaderboard

We provide the finetuning code for both GLUE tasks and ELUE tasks in static usage on ElasticBERT.

For GLUE:

cd finetune-static
bash finetune_glue.sh

For ELUE:

cd finetune-static
bash finetune_elue.sh

We provide finetuning code to apply two kind of early exiting methods on ElasticBERT.

For early exit using entropy criterion:

cd finetune-dynamic
bash finetune_elue_entropy.sh

For early exit using patience criterion:

cd finetune-dynamic
bash finetune_elue_patience.sh

Please see our paper for more details!

If you have any problems, raise an issue or contact Xiangyang Liu

If you find this repo helpful, we'd appreciate it a lot if you can cite the corresponding paper:

@inproceedings{liu-etal-2022-towards-efficient,
    title = "Towards Efficient {NLP}: A Standard Evaluation and A Strong Baseline",
    author = "Liu, Xiangyang  and
      Sun, Tianxiang  and
      He, Junliang  and
      Wu, Jiawen  and
      Wu, Lingling  and
      Zhang, Xinyu  and
      Jiang, Hao  and
      Cao, Zhao  and
      Huang, Xuanjing  and
      Qiu, Xipeng",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-main.240",
    pages = "3288--3303",
}