Measuring the Instability of Fine-Tuning
–arXiv.org Artificial Intelligence
Fine-tuning pre-trained language models on downstream tasks with varying random seeds has been shown to be unstable, especially on small datasets. Many previous studies have investigated this instability and proposed methods to mitigate it. However, most studies only used the standard deviation of performance scores (SD) as their measure, which is a narrow characterization of instability. In this paper, we analyze SD and six other measures quantifying instability at different levels of granularity. Moreover, we propose a systematic framework to evaluate the validity of these measures. Finally, we analyze the consistency and difference between different measures by reassessing existing instability mitigation methods. We hope our results will inform the development of better measurements of fine-tuning instability.
arXiv.org Artificial Intelligence
Oct-1-2023
- Country:
- Oceania > Australia
- North America
- Dominican Republic (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Washington > King County
- Europe
- Netherlands (0.04)
- France (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia > Middle East
- UAE > Abu Dhabi Emirate > Abu Dhabi (0.04)
- Genre:
- Research Report > New Finding (0.66)
- Technology: