Ouroboros: On accelerating training of transformer-based language models

Qian Yang, Zhouyuan Huo, Wenlin Wang, Heng Huang, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model parallelism is required if a model is too large to fit in a single computing device. Current methods for model parallelism either suffer from backward locking in backpropagation or are not applicable to language models. We propose the first model-parallel algorithm that speeds the training of Transformer-based language models. We also prove that our proposed algorithm is guaranteed to converge to critical points for non-convex problems. Extensive experiments on Transformer and Transformer-XL language models demonstrate that the proposed algorithm obtains a much faster speedup beyond data parallelism, with comparable or better accuracy. Code to reproduce experiments is to be found at https://github.com/LaraQianYang/Ouroboros.
Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint Dive into the research topics of 'Ouroboros: On accelerating training of transformer-based language models'. Together they form a unique fingerprint.

Cite this