Code Monkey home page Code Monkey logo

qanet-pytorch's Introduction

QANet

Re-implement QANet with PyTorch.

Usage

preprocess data python3 data_loader/squad_data.py

train python3 main.py --with_cuda --batch_size 16 --multi_gpu --use_ema

Experiment

config

hyperparameters:

  • dropout_c: 0.1
  • dropout_w: 0.05
  • d_model: 128
  • learning rate: 0.001, using warm-up scheduler
  • num_heads: 8
  • beta1: 0.8
  • beta2: 0.999

other parameters

  • word_embedding: glove.840B.300d
  • char_embedding: glove.840B.300d-char
  • grad_clip: 5.0
  • para_limit: 400
  • ques_limit: 20
  • ans_limit: 30
  • char_limit: 16

SQuAD Dataset

train dev step/train_epoch
V1.1 87360 10496 5460
v2.0 - - -
Experimenter git SHA Background Search Method Model F1 EM Notes examples/seconds
PanXie a0c87ba base model QANet 78.52 69.13 static PosEnocder, patience 30 35/s
PanXie ff39d3a without ema QANet 75.29 64.38 static PosEnocder, patience 19 35/s
PanXie 7912256 head=1 QANet 77.10 66.91 static PosEnocder, patience 25 35/s

Reference

qanet-pytorch's People

Contributors

panxiebit avatar

Stargazers

avatar avatar avatar avatar

Watchers

avatar

Forkers

homelh

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.