Rethinking Learning Rate Tuning in the Era of Large Language Models
This addresses the efficiency and quality challenges in fine-tuning LLMs for real-world applications, but it is incremental as it builds on existing benchmarking approaches.
The paper tackles the problem of learning rate tuning for fine-tuning Large Language Models (LLMs), finding that existing policies designed for traditional deep neural networks may not work well, and presents LRBench++ to benchmark and analyze these differences, with experimental validation.
Large Language Models (LLMs) represent the recent success of deep learning in achieving remarkable human-like predictive performance. It has become a mainstream strategy to leverage fine-tuning to adapt LLMs for various real-world applications due to the prohibitive expenses associated with LLM training. The learning rate is one of the most important hyperparameters in LLM fine-tuning with direct impacts on both fine-tuning efficiency and fine-tuned LLM quality. Existing learning rate policies are primarily designed for training traditional deep neural networks (DNNs), which may not work well for LLM fine-tuning. We reassess the research challenges and opportunities of learning rate tuning in the coming era of Large Language Models. This paper makes three original contributions. First, we revisit existing learning rate policies to analyze the critical challenges of learning rate tuning in the era of LLMs. Second, we present LRBench++ to benchmark learning rate policies and facilitate learning rate tuning for both traditional DNNs and LLMs. Third, our experimental analysis with LRBench++ demonstrates the key differences between LLM fine-tuning and traditional DNN training and validates our analysis.