Ray Summit 2020 has ended
View More Details for Ray Summit & Registration Information.
Please note: All Sessions are in Pacific Daylight Time (PDT), UTC-7

Wednesday, September 30 • 2:35pm - 3:05pm
EfficientBERT: Trading off Model Size and Performance - Meghana Ravikumar, SigOpt

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.

With the publication of BERT, transfer learning was suddenly accessible for NLP, unlocking a plethora of model zoos and boosting performances for domain specific problems.  Although BERT has accelerated many modeling efforts, its size is limiting. In this talk, we will explore how to reduce the size of BERT while retaining its capacity in the context of English Question Answering tasks. We’ll show how scalable hyperparameter optimization can help you tackle difficult modeling problems, draw insights, and make informed decisions.

Our approach encompasses fine-tuning, distillation, architecture search, and hyperparameter optimization at scale. First, we fine-tune BERT on SQUAD 2.0 (our teacher model) and use distillation to compress fine-tuned BERT to a smaller model (our student model). Then, combining SigOpt and Ray, we use multimetric Bayesian optimization at scale to find the optimal architecture for the student model. Finally, we explore the trade-offs of our hyperparameter decisions to draw insights for our student model’s architecture.

avatar for Meghana Ravikumar

Meghana Ravikumar

Machine Learning Engineer, SigOpt
Meghana has worked with machine learning in academia and in industry, and is happiest working on natural language processing. Prior to SigOpt, she worked in biotech, employing NLP to mine and classify biomedical literature. When she’s not reading papers, developing models/tools... Read More →

Wednesday September 30, 2020 2:35pm - 3:05pm PDT
Virtual 3