TensorX
返回文献探索

Paper · arXiv 2408.06663

Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models

Kaiser Sun, Mark Dredze

16 upvotesAugust 13, 2024arXiv 预印本
AI 摘要

Investigating pre-train-then-fine-tune paradigms reveals that additional pre-training enhances model capabilities and fine-tuning amplifies performance on incapable tasks, but may cause forgetting of prior knowledge and increased sensitivity to evaluation prompts.

pre-trainingfine-tuningintermediate pre-trained model checkpointslatent improvementdataset capabilitysupervised fine-tuningdomain knowledge

Abstract

The development of large language models leads to the formation of a pre-train-then-align paradigm, in which the model is typically pre-trained on a large text corpus and undergoes a tuning stage to align the model with human preference or downstream tasks. In this work, we investigate the relationship between pre-training and fine-tuning by fine-tuning multiple intermediate pre-trained model checkpoints. Our results on 18 datasets suggest that i) continual pre-training improves the model in a latent way that unveils after fine-tuning; ii) with extra fine-tuning, the datasets that the model does not demonstrate capability gain much more than those that the model performs well during the pre-training stage; iii) although model benefits significantly through supervised fine-tuning, it may forget previously known domain knowledge and the tasks that are not seen during fine-tuning; iv) the model resembles high sensitivity to evaluation prompts after supervised fine-tuning, but this sensitivity can be alleviated by more pre-training.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号