paper-with-me

홈 › Papers

An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models

2021-06-17 · ACL 2021 5 · Xueqing Liu, Chi Wang

The performance of fine-tuning pre-trained language models largely depends on the hyperparameter configuration. In this paper, we investigate the performance of modern hyperparameter optimization methods (HPO) on fine-tuning pre-trained language models. First, we study and report three HPO algorithms' performances on fine-tuning two state-of-the-art language models on the GLUE dataset. We find that using the same time budget, HPO often fails to outperform grid search due to two reasons: insufficient time budget and overfitting. We propose two general strategies and an experimental procedure to systematically troubleshoot HPO's failure cases. By applying the procedure, we observe that HPO can succeed with more appropriate settings in the search space and time budget; however, in certain cases overfitting remains. Finally, we make suggestions for future work. Our implementation can be found in https://github.com/microsoft/FLAML/tree/main/flaml/nlp/.

📄 PDF Abstract BibTeX arXiv:2106.09204

Code (1)

microsoft/FLAML 공식 구현

Tasks

Hyperparameter Optimization

Methods 이 논문이 사용한 방법론

HPO In machine learning, a hyperparameter is a parameter whose value is used to control learning process, and HPO is the problem of choosing a set of optimal hyperparameters for a…

Similar Papers 제목 키워드 기반

Towards Assessing the Impact of Bayesian Optimization's Own Hyperparameters

2019-08-19 · Marius Lindauer, Matthias Feurer, Katharina Eggensperger, André Biedenkapp 외

Bayesian Optimization (BO) is a common approach for hyperparameter optimization (HPO) in automated machine learning. Although it is well-accepted that HPO is crucial to obtain well-performing machine learning models, tun…

Bayesian OptimizationBIG-bench Machine LearningHyperparameter OptimizationNeural Architecture Search

Parameter Efficient Instruction Tuning: An Empirical Study

2024-11-25 · Pengfei He

Instruction tuning has become an important step for finetuning pretrained language models to better follow human instructions and generalize on various tasks. Nowadays, pretrained language models become increasingly larg…

Instruction FollowingMemorization

To tune or not to tune? An Approach for Recommending Important Hyperparameters

2021-08-30 · Mohamadjavad Bahmani, Radwa El Shawi, Nshan Potikyan, Sherif Sakr

Novel technologies in automated machine learning ease the complexity of algorithm selection and hyperparameter optimization. Hyperparameters are important for machine learning models as they significantly influence the p…

BIG-bench Machine LearningHyperparameter Optimization

A Comparative Study of Hyperparameter Tuning Methods

2024-08-29 · Subhasis Dasgupta, Jaydip Sen

The study emphasizes the challenge of finding the optimal trade-off between bias and variance, especially as hyperparameter optimization increases in complexity. Through empirical analysis, three hyperparameter tuning al…

Hyperparameter Optimizationregression

Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How

2023-06-06 · Sebastian Pineda Arango, Fabio Ferreira, Arlind Kadra, Frank Hutter 외

With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a method…

Hyperparameter Optimizationimage-classificationImage Classification