LoRA+: Efficient Low Rank Adaptation of Large Models
Soufiane Hayou, Nikhil Ghosh, Bin Yu
Abstract
In this paper, we show that Low Rank Adaptation (LoRA) as originally introduced in (Hu et al., 2021) leads to suboptimal finetuning of models with large width. This is due to the fact that adapter matrices A and B in LoRA are updated with the same learning rate in ADAM. Using scaling arguments for large width networks, we demonstrate that the same learning rate does not allow efficient feature learning. We then show that this suboptimality of LoRA can be corrected simply by setting different learning rates for the LoRA adapter matrices A and B with a well-chosen fixed ratio. We call this proposed algorithm LoRA+. In our extensive experiments, LoRA+ improves finetuning speed (up to ∼ 2X SpeedUp) and performance (1% − 2% improvements), at the same computational cost as LoRA. The code is available at https://github.com/nikhil-ghosh-berkeley/loraplus
BibTeX
@inproceedings{
hayou2024lora,
title={Lo{RA}+: Efficient Low Rank Adaptation of Large Models},
author={Soufiane Hayou and Nikhil Ghosh and Bin Yu},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=NEv8YqBROO}
}