Empirical Analysis of Efficient Fine-Tuning Methods for Large Pre-Trained Language Models
Fine-tuning large pre-trained language models for downstream tasks remains a critical challenge in natural language processing. This paper presents an empirical analysis comparing two efficient fine-tuning methods - BitFit and adapter modules - to standard full model fine-tuning. Experiments conducted on GLUE benchmark datasets (MRPC, COLA, STS-B) reveal several key insights. The BitFit approach, which trains only bias terms and task heads, matches full fine-tuning performance across varying amounts of training data and time constraints. It demonstrates remarkable stability even with only 30\% of data, outperforming full fine-tuning at intermediate data levels. Adapter modules exhibit high variability, with inconsistent gains over default models. The findings indicate BitFit offers an attractive balance between performance and parameter efficiency. Our work provides valuable perspectives on model tuning, emphasizing robustness and highlighting BitFit as a promising alternative for resource-constrained or streaming task settings. The analysis offers actionable guidelines for efficient adaptation of large pre-trained models, while illustrating open challenges in stabilizing techniques like adapter modules.
Code (0)
등록된 구현이 없습니다.
Tasks
CoLAMRPCSTSSTS-BMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models
Multimodal large language models (MLLMs) fine-tuned with multimodal instruction datasets have demonstrated remarkable capabilities in multimodal tasks. However, fine-tuning all parameters of MLLMs has become challenging …
Hallucinationparameter-efficient fine-tuningDifferentially 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 ModelStrong Baselines for Parameter Efficient Few-Shot Fine-tuning
Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase on a set of base classes. Recent works have shown that simply fine-tuning a p…
Few-Shot Image Classificationimage-classificationImage Classificationparameter-efficient fine-tuningNew Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, bot…
parameter-efficient fine-tuningA Stability Analysis of Fine-Tuning a Pre-Trained Model
Fine-tuning a pre-trained model (such as BERT, ALBERT, RoBERTa, T5, GPT, etc.) has proven to be one of the most promising paradigms in recent NLP research. However, numerous recent works indicate that fine-tuning suffers…