2022/11/30 by Rui Pan, Pan, Rui, Shizhe Diao +5 · 2 citations
Computer Science · Mathematics · #Code (set theory) #Computation and Language (cs.CL) #Computer science #Documentation #FOS: Computer and information sciences #FOS: Mathematics #License #MIT License #Machine Learning (cs.LG) #Machine Learning and Data Classification #Natural Language Processing Techniques #Operating system #Optimization and Control (math.OC) #Programming language #Set (abstract data type) #Source code #Topic Modeling #World Wide Web #cs.CL #cs.LG #math.OC
paper · pdf · doi:10.48550/arxiv.2211.17201
published in arXiv (Cornell University) (Cornell University)
arxiv created 2022/11/30 · openalex publication_date 2022/11/30 · arxiv updated 2022/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we present ExtremeBERT, a toolkit for accelerating and customizing BERT pretraining. Our goal is to provide an easy-to-use BERT pretraining toolkit for the research community and industry. Thus, the pretraining of popular language models on customized datasets is affordable with limited resources. Experiments show that, to achieve the same or better GLUE scores, the time cost of our toolkit is over 6× times less for BERT Base and 9× times less for BERT Large when compared with the original BERT paper. The documentation and code are released at https://github.com/extreme-bert/extreme-bert under the Apache-2.0 license.