# AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning

Source: [AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning](<https://www.sota2.com/research/paper/68fa75f51e209131cea6aa7f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:11.536Z

Authors: Yifan Yang, Kai Zhen, Ershad Banijamal, Athanasios Mouchtaris, Zheng Zhang

Published: 2024-06-26T04:33:13.000Z

## Abstract

Fine-tuning large language models (LLMs) has achieved remarkable performance across various natural language processing tasks, yet it demands more and more memory as model sizes keep growing. To address this issue, the recently proposed Memory-efficient Zeroth-order (MeZO) methods attempt to fine-tune LLMs using only forward passes, thereby avoiding the need for a backpropagation graph. However, significant performance drops and a high risk of divergence have limited their widespread adoption. In this paper, we propose the Adaptive Zeroth-order Tensor-Train Adaption (AdaZeta) framework, specifically designed to improve the performance and convergence of the ZO methods. To enhance dimension-dependent ZO estimation accuracy, we introduce a fast-forward, low-parameter tensorized adapter. To tackle the frequently observed divergence issue in large-scale ZO fine-tuning tasks, we propose an adaptive query number schedule that guarantees convergence. Detailed theoretical analysis and extensive experimental results on Roberta-Large and Llama-2-7B models substantiate the efficacy of our AdaZeta framework in terms of accuracy, memory efficiency, and convergence speed.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Natural Language Understanding on SuperGLUE 1,000 examples](<https://www.sota2.com/research/sota/natural-language-understanding-on-superglue-1-000-examples.md>): Natural Language Understanding; SuperGLUE 1,000 examples; BoolQ Accuracy: 79.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.18060>)

[PDF](<https://arxiv.org/pdf/2406.18060.pdf>)
