<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nawrot-2023-nanot5">
    <titleInfo>
        <title>nanoT5: Fast &amp; Simple Pre-training and Fine-tuning of T5 Models with Limited Resources</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Piotr</namePart>
        <namePart type="family">Nawrot</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Liling</namePart>
            <namePart type="family">Tan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dmitrijs</namePart>
            <namePart type="family">Milajevs</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Geeticka</namePart>
            <namePart type="family">Chauhan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jeremy</namePart>
            <namePart type="family">Gwinnup</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Elijah</namePart>
            <namePart type="family">Rippeth</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>State-of-the-art language models like T5 have revolutionized the NLP landscape, but their computational demands hinder a large portion of the research community. To address this challenge, we present nanoT5, a specially-optimized PyTorch framework for efficient pre-training and fine-tuning of T5 models. Drawing on insights from optimizer differences and prioritizing efficiency, nanoT5 allows a T5-Base model to be pre-trained on a single GPU in just 16 hours, without any loss in performance. With the introduction of this open-source framework, we hope to widen the accessibility to language modelling research and cater to the community’s demand for more user-friendly T5 (Encoder-Decoder) implementations. We make our contributions, including configurations, codebase, pre-training insights, and pre-trained models, available to the public.</abstract>
    <identifier type="citekey">nawrot-2023-nanot5</identifier>
    <identifier type="doi">10.18653/v1/2023.nlposs-1.11</identifier>
    <location>
        <url>https://aclanthology.org/2023.nlposs-1.11</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>95</start>
            <end>101</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T nanoT5: Fast & Simple Pre-training and Fine-tuning of T5 Models with Limited Resources
%A Nawrot, Piotr
%Y Tan, Liling
%Y Milajevs, Dmitrijs
%Y Chauhan, Geeticka
%Y Gwinnup, Jeremy
%Y Rippeth, Elijah
%S Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F nawrot-2023-nanot5
%X State-of-the-art language models like T5 have revolutionized the NLP landscape, but their computational demands hinder a large portion of the research community. To address this challenge, we present nanoT5, a specially-optimized PyTorch framework for efficient pre-training and fine-tuning of T5 models. Drawing on insights from optimizer differences and prioritizing efficiency, nanoT5 allows a T5-Base model to be pre-trained on a single GPU in just 16 hours, without any loss in performance. With the introduction of this open-source framework, we hope to widen the accessibility to language modelling research and cater to the community’s demand for more user-friendly T5 (Encoder-Decoder) implementations. We make our contributions, including configurations, codebase, pre-training insights, and pre-trained models, available to the public.
%R 10.18653/v1/2023.nlposs-1.11
%U https://aclanthology.org/2023.nlposs-1.11
%U https://doi.org/10.18653/v1/2023.nlposs-1.11
%P 95-101

Markdown (Informal)

[nanoT5: Fast & Simple Pre-training and Fine-tuning of T5 Models with Limited Resources](https://aclanthology.org/2023.nlposs-1.11) (Nawrot, NLPOSS-WS 2023)

• nanoT5: Fast & Simple Pre-training and Fine-tuning of T5 Models with Limited Resources (Nawrot, NLPOSS-WS 2023)

ACL

• Piotr Nawrot. 2023. nanoT5: Fast & Simple Pre-training and Fine-tuning of T5 Models with Limited Resources. In Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023), pages 95–101, Singapore. Association for Computational Linguistics.