Atli Kosson, Bettina Messmer, Martin Jaggi. Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training. In Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, Cheng Zhang 0005, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024. 2024. [doi]
@inproceedings{KossonMJ24-0,
title = {Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training},
author = {Atli Kosson and Bettina Messmer and Martin Jaggi},
year = {2024},
url = {http://papers.nips.cc/paper_files/paper/2024/hash/059445c2d5b3ef918079851628fef1d6-Abstract-Conference.html},
researchr = {https://researchr.org/publication/KossonMJ24-0},
cites = {0},
citedby = {0},
booktitle = {Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024},
editor = {Amir Globersons and Lester Mackey and Danielle Belgrave and Angela Fan and Ulrich Paquet and Jakub M. Tomczak and Cheng Zhang 0005},
}