Crafting Efficient Fine-Tuning Strategies for Large Language Models
Preprint
Abstract
This paper addresses the challenges of efficiently fine-tuning large language models (LLMs) by exploring data efficiency and hyperparameter optimization. We investigate the minimum data required for effective fine-tuning and propose a novel hyperparameter optimization method that leverages early-stage model performance. Our experiments demonstrate that fine-tuning with as few as 200 samples can improve model accuracy from 70\% to 88\% in a product attribute extraction task. We identify a saturation point of approximately 6,500 samples, beyond which additional data yields diminishing returns. Our proposed bayesian hyperparameter optimization method, which evaluates models at 20\% of total training time, correlates strongly with final model performance, with 4 out of 5 top early-stage models remaining in the top 5 at completion. This approach led to a 2\% improvement in accuracy over baseline models when evaluated on an independent test set. These findings offer actionable insights for practitioners, potentially reducing computational load and dependency on extensive datasets while enhancing overall performance of fine-tuned LLMs.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- LoRA dropout as a sparsity regularizer for overfitting reductionKnowledge-Based Systems, 2025
- LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction2024
- Rethinking Learning Rate Tuning in the Era of Large Language Models2023
- Parameter-efficient fine-tuning of large-scale pre-trained language modelsNature Machine Intelligence, 2023
- Frugal Optimization for Cost-related HyperparametersProceedings of the AAAI Conference on Artificial Intelligence, 2021