PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark
This work addresses the need for standardized benchmarking in PEFT methods to improve accessibility and efficiency in fine-tuning large language models, though it is incremental as it builds on existing PEFT approaches.
The authors tackled the problem of limited and non-reproducible evaluations for Parameter-Efficient Fine-Tuning (PEFT) methods by introducing PEFT-Bench, a unified benchmark that evaluates 7 PEFT methods across 27 NLP datasets and includes a new metric (PSCP) to account for training and inference costs.
Despite the state-of-the-art performance of Large Language Models (LLMs) achieved on many tasks, their massive scale often leads to high computational and environmental costs, limiting their accessibility. Parameter-Efficient Fine-Tuning (PEFT) methods address this challenge by reducing the number of trainable parameters while maintaining strong downstream performance. Despite the advances in PEFT methods, current evaluations remain limited (in terms of evaluated models and datasets) and difficult to reproduce. To bridge this gap, we introduce PEFT-Bench, a unified end-to-end benchmark for evaluating diverse PEFT methods on autoregressive LLMs. We demonstrate its usage across 27 NLP datasets and 7 PEFT methods. To account for different PEFT training and inference factors, we also introduce the PEFT Soft Cost Penalties (PSCP) metric, which takes trainable parameters, inference speed, and training memory usage into account.