Web: http://arxiv.org/abs/2203.05482

June 23, 2022, 1:12 a.m. | Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair C

cs.CL updates on arXiv.org arxiv.org

The conventional recipe for maximizing model accuracy is to (1) train
multiple models with various hyperparameters and (2) pick the individual model
which performs best on a held-out validation set, discarding the remainder. In
this paper, we revisit the second step of this procedure in the context of
fine-tuning large pre-trained models, where fine-tuned models often appear to
lie in a single low error basin. We show that averaging the weights of multiple
models fine-tuned with different hyperparameter configurations often …

accuracy arxiv fine inference lg model models time

More from arxiv.org / cs.CL updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY