"Investigating the Limitations of Transformers with Simple Arithmetic Tasks", 2021

Overview

transformers-arithmetic

This repository contains the code to reproduce the experiments from the paper:

Nogueira, Jiang, Lin "Investigating the Limitations of Transformers with Simple Arithmetic Tasks", 2021

First, install the required packages:

pip install -r requirements.txt

The command below trains and evaluates a T5-base model on the task of adding up to 15-digits:

python main.py \
    --output_dir=. \
    --model_name_or_path=t5-base \
    --operation=addition \
    --orthography=10ebased \
    --balance_train \
    --balance_val \
    --train_size=100000 \
    --val_size=10000 \
    --test_size=10000 \
    --min_digits_train=2 \
    --max_digits_train=15 \
    --min_digits_test=2 \
    --max_digits_test=15 \
    --base_number=10 \
    --seed=1 \
    --train_batch_size=4 \
    --accumulate_grad_batches=32 \
    --val_batch_size=32 \
    --max_seq_length=512 \
    --num_workers=4 \
    --gpus=1 \
    --optimizer=AdamW \
    --lr=3e-4 \
    --weight_decay=5e-5 \
    --scheduler=StepLR \
    --t_0=2 \
    --t_mult=2 \
    --gamma=1.0 \
    --step_size=1000 \
    --max_epochs=20 \
    --check_val_every_n_epoch=2 \
    --amp_level=O0 \
    --precision=32 \
    --gradient_clip_val=1.0

This training should take 10 hours on a V100 GPU.

The exact match on the test set should be 1:

--------------------------------------------------------------------------------
DATALOADER:0 TEST RESULTS
{'test_exact_match': 1.0000}
--------------------------------------------------------------------------------
Owner
Castorini
Deep learning for natural language processing and information retrieval at the University of Waterloo
Castorini
A 10000+ hours dataset for Chinese speech recognition

A 10000+ hours dataset for Chinese speech recognition

309 Dec 16, 2022
This is the writeup of all the challenges from Advent-of-cyber-2019 of TryHackMe

Advent-of-cyber-2019-writeup This is the writeup of all the challenges from Advent-of-cyber-2019 of TryHackMe https://tryhackme.com/shivam007/badges/c

shivam danawale 5 Jul 17, 2022
Skipgram Negative Sampling in PyTorch

PyTorch SGNS Word2Vec's SkipGramNegativeSampling in Python. Yet another but quite general negative sampling loss implemented in PyTorch. It can be use

Jamie J. Seol 287 Dec 14, 2022
숭실대학교 컴퓨터학부 전공종합설계프로젝트

✨ 시각장애인을 위한 버스도착 알림 장치 ✨ 👀 개요 현대 사회에서 대중교통 위치 정보를 이용하여 사람들이 간단하게 이용할 대중교통의 정보를 얻고 쉽게 대중교통을 이용할 수 있다. 해당 정보는 각종 어플리케이션과 대중교통 이용시설에서 위치 정보를 제공하고 있지만 시각

taegyun 3 Jan 25, 2022
Tokenizer - Module python d'analyse syntaxique et de grammaire, tokenization

Tokenizer Le Tokenizer est un analyseur lexicale, il permet, comme Flex and Yacc par exemple, de tokenizer du code, c'est à dire transformer du code e

Manolo 1 Aug 15, 2022
Implementaion of our ACL 2022 paper Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation This is the implementaion of our paper: Bridging the

hezw.tkcw 20 Dec 12, 2022
Easy to use, state-of-the-art Neural Machine Translation for 100+ languages

EasyNMT - Easy to use, state-of-the-art Neural Machine Translation This package provides easy to use, state-of-the-art machine translation for more th

Ubiquitous Knowledge Processing Lab 748 Jan 06, 2023
ACL'2021: Learning Dense Representations of Phrases at Scale

DensePhrases DensePhrases is an extractive phrase search tool based on your natural language inputs. From 5 million Wikipedia articles, it can search

Princeton Natural Language Processing 540 Dec 30, 2022
Transformers implementation for Fall 2021 Clinic

Installation Download miniconda3 if not already installed You can check by running typing conda in command prompt. Use conda to create an environment

Aakash Tripathi 1 Oct 28, 2021
Pretrain CPM - 大规模预训练语言模型的预训练代码

CPM-Pretrain 版本更新记录 为了促进中文自然语言处理研究的发展,本项目提供了大规模预训练语言模型的预训练代码。项目主要基于DeepSpeed、Megatron实现,可以支持数据并行、模型加速、流水并行的代码。 安装 1、首先安装pytorch等基础依赖,再安装APEX以支持fp16。 p

Tsinghua AI 37 Dec 06, 2022
Generate product descriptions, blogs, ads and more using GPT architecture with a single request to TextCortex API a.k.a Hemingwai

TextCortex - HemingwAI Generate product descriptions, blogs, ads and more using GPT architecture with a single request to TextCortex API a.k.a Hemingw

TextCortex AI 27 Nov 28, 2022
Final Project for the Intel AI Readiness Boot Camp NLP (Jan)

NLP Boot Camp (Jan) Synopsis Full Name: Prameya Mohanty Name of your School: Delhi Public School, Rourkela Class: VIII Title of the Project: iTransect

TheCodingHub 1 Feb 01, 2022
nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using Pytorch

nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using Pytorch. Most of the models in NLP were implemented with less than 100 lines of code.(except comments or blank li

Tae-Hwan Jung 11.9k Jan 08, 2023
Torchrecipes provides a set of reproduci-able, re-usable, ready-to-run RECIPES for training different types of models, across multiple domains, on PyTorch Lightning.

Recipes are a standard, well supported set of blueprints for machine learning engineers to rapidly train models using the latest research techniques without significant engineering overhead.Specifica

Meta Research 193 Dec 28, 2022
The training code for the 4th place model at MDX 2021 leaderboard A.

The training code for the 4th place model at MDX 2021 leaderboard A.

Chin-Yun Yu 32 Dec 18, 2022
VampiresVsWerewolves - Our Implementation of a MiniMax algorithm with alpha beta pruning in the context of an in-class competition

VampiresVsWerewolves Our Implementation of a MiniMax algorithm with alpha beta pruning in the context of an in-class competition. Our Algorithm finish

Shawn 1 Jan 21, 2022
BERT, LDA, and TFIDF based keyword extraction in Python

BERT, LDA, and TFIDF based keyword extraction in Python kwx is a toolkit for multilingual keyword extraction based on Google's BERT and Latent Dirichl

Andrew Tavis McAllister 41 Dec 27, 2022
Proquabet - Convert your prose into proquints and then you essentially have Vogon poetry

Proquabet Turn your prose into a constant stream of encrypted and meaningless-so

Milo Fultz 2 Oct 10, 2022
keras implement of transformers for humans

keras implement of transformers for humans

苏剑林(Jianlin Su) 4.8k Jan 03, 2023
Document processing using transformers

Doc Transformers Document processing using transformers. This is still in developmental phase, currently supports only extraction of form data i.e (ke

Vishnu Nandakumar 13 Dec 21, 2022