Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum

Item #:

079017-1139

Details

DOI: https://doi.org/10.52202/079017-1139
Author(s): Jen-Hao Chang, Cem Koc, Chun-Liang Li, Hadi Pouransari, Vaishaal Shankar, Oncel Tuzel, Pavan Vasu
Pages: 36121-36147 (27 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-1139
Author(s): Jen-Hao Chang, Cem Koc, Chun-Liang Li, Hadi Pouransari, Vaishaal Shankar, Oncel Tuzel, Pavan Vasu
Pages: 36121-36147 (27 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)