When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method

TL;DR

This paper systematically studies how different scaling factors influence large language model finetuning performance, revealing that model size scaling benefits finetuning more than data scaling, with implications for choosing finetuning methods.

Contribution

It provides a comprehensive analysis of the scaling behaviors of various finetuning methods across different model sizes and tasks, highlighting the importance of model scaling over data scaling.

Findings

Finetuning follows a power-based multiplicative scaling law.

Model scaling benefits finetuning more than data scaling.

Parameter efficient tuning methods are generally less effective.

Abstract

While large language models (LLMs) often adopt finetuning to unlock their capabilities for downstream applications, our understanding on the inductive biases (especially the scaling properties) of different finetuning methods is still limited. To fill this gap, we conduct systematic experiments studying whether and how different scaling factors, including LLM model size, pretraining data size, new finetuning parameter size and finetuning data size, affect the finetuning performance. We consider two types of finetuning -- full-model tuning (FMT) and parameter efficient tuning (PET, including prompt tuning and LoRA), and explore their scaling behaviors in the data-limited regime where the LLM model size substantially outweighs the finetuning data size. Based on two sets of pretrained bilingual LLMs from 1B to 16B and experiments on bilingual machine translation and multilingual summarization benchmarks, we find that 1) LLM finetuning follows a powerbased multiplicative joint scaling law between finetuning data size and each other scaling factor; 2) LLM finetuning benefits more from LLM model scaling than pretraining data scaling, and PET parameter scaling is generally ineffective; and 3) the optimal finetuning method is highly task- and finetuning data-dependent. We hope our findings could shed light on understanding, selecting and developing LLM finetuning methods.