Paper link:
https://arxiv.org/pdf/2404.15758
Table of contents:
- Introduction
- Related Work
- Methodology
- Results
- LoRA learns less
- LoRA forgets less
- LoRA regularization properties
- LoRA rank dynamics
- Discussion
- Practical LoRA tips
- Future research directions
- Questions
1. Introduction
The common assumption is that LoRA maintains accuracy as a fully finetuned model (FFT) while reducing trainable parameters and compute usage on a new target domain. Seems too good to be true?
Few papers have shown a direct model-to-model comparison with billions of parameters between LoRA and FFT.
The current available papers in this field:
- some of them showed mixed results
- other papers were using older models and benchmark (i.e. RoBERTa model and GLUE benchmark) which are not too relevant with contemporary LLMs.
- others also reported that LoRA struggles in more sensitive domain tasks like coding.
The authors hence performed a rigorous analysis on the performance on LoRA finetuning and FFT Llama-2 7B models.