Giter VIP home page Giter VIP logo

clrp-solution's Introduction

CLRP-solution

Requirements:

torch==1.9.0+cu111
transformers==4.9.2

Tested on a RTX A6000 with 48GB VRAM

Prep:

Just run ./download_extra_data.sh or

Download
Children's Book Test from:
https://research.fb.com/downloads/babi/
Simple Wiki Dump from:
https://github.com/LGDoor/Dump-of-Simple-English-Wiki
and save it as follows
./extra_data/cbt_test.txt
./extra_data/cbt_train.txt
./extra_data/cbt_valid.txt
./extra_data/simple_english_wiki.txt

CLRP training data (need to download manually from Kaggle) goes to
./data/train.csv
./data/test.csv

Train from scratch:

./run_train.sh
takes about 30 hours

Predict:

python 4.predict.py ./{path_to_source_file}.csv ./{path_to_save}.csv 3 0 ./models/roberta_2/ ./models/deberta_1/ ./models/deberta_2/
make sure the column name is 'excerpt' in source csv file

Solution writeup:

https://www.kaggle.com/c/commonlitreadabilityprize/discussion/258095

clrp-solution's People

Contributors

danielhuxc avatar ncduy0303 avatar

Stargazers

avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.