Zeroth-Order Fine-Tuning of LLMs in Random Subspaces
Fine-tuning Large Language Models (LLMs) has proven effective for a variety of downstream tasks. However, as LLMs grow in size, the memory demands for backpropagation become increasingly prohibitive. Zeroth-order (ZO) optimization methods offer a memory-efficient alternative by using forward passes to estimate gradients, but the variance of gradient estimates typically scales linearly with the model's parameter dimension$\unicode{x2013}$a significant issue for LLMs. In this paper, we propose the random Subspace Zeroth-order (SubZero) optimization to address the challenges posed by LLMs' high dimensionality. We introduce a low-rank perturbation tailored for LLMs that significantly reduces memory consumption while improving training performance. Additionally, we prove that our gradient estimation closely approximates the backpropagation gradient, exhibits lower variance than traditional ZO methods, and ensures convergence when combined with SGD. Experimental results show that SubZero enhances fine-tuning performance and achieves faster convergence compared to standard ZO approaches like MeZO across various language modeling tasks.
Code (1)
Tasks
Language ModelingLanguage ModellingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning
Fine-tuning on task-specific datasets is a widely-embraced paradigm of harnessing the powerful capability of pretrained LLMs for various downstream tasks. Due to the popularity of LLMs fine-tuning and its accompanying pr…
Language ModelingLanguage ModellingLarge Language ModelConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the memory overhead of backpropagation. However, it converges slowly due to …
ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation
Federated fine-tuning of large language models (LLMs) enables collaborative tuning across distributed clients. However, due to the large size of LLMs, local updates in federated learning (FL) may incur substantial video …
Federated LearningLearning a Zeroth-Order Optimizer for Fine-Tuning LLMs
Zeroth-order optimizers have recently emerged as an attractive approach for fine-tuning large language models (LLMs), as they avoid backpropagation and can substantially reduce memory overhead relative to standard first-…
Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer
Fine-tuning large language models (LLMs) with classic first-order optimizers entails prohibitive GPU memory due to the backpropagation process. Recent works have turned to zeroth-order optimizers for fine-tuning, which s…
GPU