paper-with-me

홈 › Papers

Empirical Analysis of Efficient Fine-Tuning Methods for Large Pre-Trained Language Models

2024-01-08 · Nigel Doering, Cyril Gorlla, Trevor Tuttle, Adhvaith Vijay

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.

📄 PDF Abstract BibTeX arXiv:2401.04051

Code (0)

등록된 구현이 없습니다.

Tasks

CoLAMRPCSTSSTS-B

Methods 이 논문이 사용한 방법론

COLA COLA is a self-supervised pre-training approach for learning a general-purpose representation of audio. It is based on contrastive learning: it learns a representation which…
Adapter 설명 없음

Similar Papers 제목 키워드 기반

An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models

2024-06-07 · Xiongtao Zhou, Jie He, Yuhua Ke, Guangyao Zhu 외

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-tuning

Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning

2024-02-12 · Z Liu, J Lou, W Bao, Y Hu 외

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 Model

Strong Baselines for Parameter Efficient Few-Shot Fine-tuning

2023-04-04 · Samyadeep Basu, Daniela Massiceti, Shell Xu Hu, Soheil Feizi

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-tuning

New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework

2026-04-10 · Shaocong Ma, Peiran Yu, Heng Huang arxiv

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-tuning

A Stability Analysis of Fine-Tuning a Pre-Trained Model

2023-01-24 · Zihao Fu, Anthony Man-Cho So, Nigel Collier

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…