Git Product home page Git Product logo

dps's Introduction

DPS

Source code for NeurIPS 2022 Long paper: Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

1. Environments

  • python: 3.8.10
  • CUDA Version: 11.4

2. Dependencies

  • torch==1.8.0
  • datasets==1.8.0
  • transformers==4.7.0

3. Training

cd script

3.1 Fine-tuning on GLUE

bash run_glue.sh

3.2 Fine-tuning on out domain

bash run_out_of_domain.sh

3.3 Fine-tuning on low resource

bash run_low_resource.sh

4. Citation

If you use this work or code, please kindly cite the following paper:

@inproceedings{haojiefine,
  title={Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively},
  author={Haojie, Zhang and Li, Ge and Li, Jia and Zhang, Zhongjin and Zhu, Yuqi and Jin, Zhi},
  booktitle={Advances in Neural Information Processing Systems}
}

dps's People

Contributors

zhanghaojie077 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

dps's Issues

No glue.py in scripts.

Line number 244 in run_trainer.py:
datasets = load_dataset("glue.py", data_args.task_name)

But there is no file named glue.py there in scripts. How to resolve this?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.