Papers
arxiv:2402.16141

PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization

Published on Feb 25, 2024
Authors:
,
,
,
,
,
,
,
,
,

Abstract

Supervised fine-tuning is the most common method to adapt large language models (LLMs) to downstream tasks, but full fine-tuning LLMs requires massive computational resources. Recently, parameter-efficient fine-tuning (PEFT) methods have been widely studied due to its cost-effectiveness. LoRA is one of the most widely used methods, which assumes that the optimization process is essentially low-dimensional. Although LoRA fine-tuning is effective, there is still a performance gap compared to full fine-tuning, since its weight update is limited to low-rank matrices. In order to break the low-rank bottleneck in LoRA Optimization, we propose Periodic<PRE_TAG>LoRA (PLoRA)</POST_TAG>, which accumulates low-rank update matrices multiple times to achieve a higher update rank. PLoRA has multiple training stages. During each stage, we still update only the LoRA weights. However, at the end of each stage, we unload the LoRA weights into the backbone parameters and then reinitialize the LoRA states. Experimental results show that PLoRA has stronger learning ability, approximately 1.8 times that of LoRA's learning ability at most, but it does not increase memory usage. Further, we introduce a momentum-based unloading strategy for PLoRA to mitigate the training instability.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2402.16141 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2402.16141 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2402.16141 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.