LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation

Seyedarmin Azizi, Souvik Kundu, Massoud Pedram


Abstract
Low-rank adaptation (LoRA) has become the default approach to fine-tune large language models (LLMs) due to its significant reduction in trainable parameters. However, trainable parameter demand for LoRA increases with increasing model embedding dimensions, leading to high compute costs. Additionally, its backward updates require storing high-dimensional intermediate activations and optimizer states, demanding high peak GPU memory. In this paper, we introduce _LaMDA_, a novel approach to fine-tuning large language models, which leverages low-dimensional adaptation to achieve significant reductions in trainable parameters and peak GPU memory footprint. LaMDA freezes a first projection matrix (PMA) in the adaptation path while introducing a low-dimensional trainable square matrix, resulting in substantial reductions in trainable parameters and peak GPU memory usage. LaMDA gradually freezes a second projection matrix (PMB) during the early fine-tuning stages, reducing the compute cost associated with weight updates to enhance parameter efficiency further.We also present an enhancement, LaMDA++, incorporating a “lite-weight” adaptive rank allocation for the LoRA path via normalized spectrum analysis of pre-trained model weights. We evaluate LaMDA/LaMDA++ across various tasks, including natural language understanding with the GLUE benchmark, text summarization, natural language generation, and complex reasoning on different LLMs.Results show that LaMDA matches or surpasses the performance of existing alternatives while requiring up to **17.7×** fewer parameter updates and up to **1.32×** lower peak GPU memory usage during fine-tuning. Code will be publicly available at https://github.com/ArminAzizi98/LaMDA.
Anthology ID:
2024.findings-emnlp.563
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9635–9646
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.563
DOI:
Bibkey:
Cite (ACL):
Seyedarmin Azizi, Souvik Kundu, and Massoud Pedram. 2024. LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9635–9646, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation (Azizi et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.563.pdf