{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T04:06:04Z","timestamp":1750824364319,"version":"3.41.0"},"reference-count":8,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,5]]},"DOI":"10.1109\/cscwd64889.2025.11033565","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:24:40Z","timestamp":1750699480000},"page":"1526-1530","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Training of Large Language Models on Legacy GPUs with HetSeq and PyTorch"],"prefix":"10.1109","author":[{"given":"Bruno Leite","family":"Franco","sequence":"first","affiliation":[{"name":"Graduate Program in Applied Informatics Pontifícia Universidade Cató lica do Paraná,Curitiba,PR,Brazil"}]},{"given":"Edson Em\u00edlio","family":"Scalabrin","sequence":"additional","affiliation":[{"name":"Graduate Program in Applied Informatics Pontifícia Universidade Cató lica do Paraná,Curitiba,PR,Brazil"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3700439"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/12107.001.0001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2022.104745"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.emnlp-main.831","article-title":"How to Train BERT with an Academic Budget","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Izsak","year":"2021"},{"key":"ref5","first-page":"5958","article-title":"Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","volume-title":"International Conference on Machine Learning","volume":"1","author":"Li","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17813"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/isbi.2008.4541126"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2012.2211477"}],"event":{"name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","start":{"date-parts":[[2025,5,5]]},"location":"Compiegne, France","end":{"date-parts":[[2025,5,7]]}},"container-title":["2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11033175\/11033221\/11033565.pdf?arnumber=11033565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:17:10Z","timestamp":1750745830000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11033565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,5]]},"references-count":8,"URL":"https:\/\/doi.org\/10.1109\/cscwd64889.2025.11033565","relation":{},"subject":[],"published":{"date-parts":[[2025,5,5]]}}}