XYZ Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing

Conglong Li, Zhewei Yao, Xiaoxia Wu, Minjia Zhang, Connor Holmes, Cheng Li, Yuxiong He

Keywords: data efficiency, training efficiency, foundation model, pretraining, finetuning, language model, GPT-3, BERT, ViT

TL;DR: We propose a framework that reduces GPT-3/BERT pretraining and GPT-2/ViT finetuning data and cost with boosted model quality via new innovations on data sampling and data routing.

Abstract: Recent advances on deep learning models come at the price of formidable training cost. The increasing model size is one of the root causes, but another less-emphasized fact is that data scale is actually increasing at a similar speed as model scale, and the training cost is proportional to both of them. Compared to the rapidly evolving model architecture, how to efficiently use the training data (especially for the expensive foundation model pretraining) is both less explored and difficult to realize due to the lack of a convenient framework that focus on data efficiency capabilities. To this end, we present XYZ Data Efficiency, a framework that makes better use of data, increases training efficiency, and improves model quality. Specifically, we propose and combine two data efficiency techniques: efficient data sampling via a general curriculum learning library, and efficient data routing via a novel random layerwise token dropping technique. For GPT-3 1.3B language model pretraining, our work achieves 12.5x less data/time/cost (`$`3.7K if rent on Azure), while still maintaining 95% of model quality compared to baseline with full data and cost (`$`46.3K). For GPT-3 1.3B and BERT-large pretraining, our work can also achieve the same model quality with up to 2x less data/time/cost, or achieve better model quality under same data/time/cost. XYZ Data Efficiency is easy to use and tune, enabling us to easily apply it and verify its benefit on additional tasks including GPT-3 MoE model pretraining and small-scale GPT-2/ViT finetuning.

Submission Number: 10787