Paper · arXiv 2408.06663
Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models
Kaiser Sun, Mark Dredze
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.
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.