Papers
arxiv:2406.06623
Spectrum: Targeted Training on Signal to Noise Ratio
Published on Jun 7
Authors:
Abstract
Efficiently post-training large language models remains a challenging task due to the vast computational resources required. We present Spectrum, a method that accelerates LLM training by selectively targeting layer modules based on their signal-to-noise ratio (SNR), and freezing the remaining modules. Our approach, which utilizes an algorithm to compute module SNRs prior to training, has shown to effectively match the performance of full fine-tuning while reducing GPU memory usage. Experiments comparing Spectrum to existing methods such as QLoRA demonstrate its effectiveness in terms of model quality and VRAM efficiency in distributed environments.
Community
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2406.06623 in a dataset README.md to link it from this page.