TY - GEN
T1 - An empirical study on hyperparameter optimization for fine-tuning pre-trained language models
AU - Liu, Xueqing
AU - Wang, Chi
N1 - Publisher Copyright: © 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - 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/.
AB - 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/.
UR - http://www.scopus.com/inward/record.url?scp=85118946194&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85118946194&partnerID=8YFLogxK
M3 - Conference contribution
T3 - ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
SP - 2286
EP - 2300
BT - ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021
Y2 - 1 August 2021 through 6 August 2021
ER -