Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping

Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping Chenghao Yang author Xuezhe Ma author 2022-12 text Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Yoav Goldberg editor Zornitsa Kozareva editor Yue Zhang editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates conference publication yang-ma-2022-improving 10.18653/v1/2022.emnlp-main.322 https://aclanthology.org/2022.emnlp-main.322/ 2022-12 4854 4859