LoRA+: Efficient Low Rank Adaptation of Large Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hayou, Soufiane, Ghosh, Nikhil, Yu, Bin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917713295704064
author Hayou, Soufiane
Ghosh, Nikhil
Yu, Bin
author_facet Hayou, Soufiane
Ghosh, Nikhil
Yu, Bin
contents 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 (embedding dimension). This is due to the fact that adapter matrices A and B in LoRA are updated with the same learning rate. Using scaling arguments for large width networks, we demonstrate that using the same learning rate for A and B 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 ratio. We call this proposed algorithm LoRA$+$. In our extensive experiments, LoRA$+$ improves performance (1-2 $\%$ improvements) and finetuning speed (up to $\sim$ 2X SpeedUp), at the same computational cost as LoRA.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LoRA+: Efficient Low Rank Adaptation of Large Models
Hayou, Soufiane
Ghosh, Nikhil
Yu, Bin
Machine Learning
Artificial Intelligence
Computation and Language
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 (embedding dimension). This is due to the fact that adapter matrices A and B in LoRA are updated with the same learning rate. Using scaling arguments for large width networks, we demonstrate that using the same learning rate for A and B 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 ratio. We call this proposed algorithm LoRA$+$. In our extensive experiments, LoRA$+$ improves performance (1-2 $\%$ improvements) and finetuning speed (up to $\sim$ 2X SpeedUp), at the same computational cost as LoRA.
title LoRA+: Efficient Low Rank Adaptation of Large Models
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2402.12354