Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping. Yang, C. & Ma, X. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4854–4859, Abu Dhabi, United Arab Emirates, December, 2022. Association for Computational Linguistics.
bibtex   
@inproceedings{yang-ma-2022-improving,
    title = "Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping",
    author = "Yang, Chenghao  and
      Ma, Xuezhe",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    pages = "4854--4859",
}

Downloads: 0