Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pouransari, Hadi, Li, Chun-Liang, Chang, Jen-Hao Rick, Vasu, Pavan Kumar Anasosalu, Koc, Cem, Shankar, Vaishaal, Tuzel, Oncel
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2405.13226