Vanishing Gradients in Reinforcement Finetuning of Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Razin, Noam, Zhou, Hattie, Saremi, Omid, Thilak, Vimal, Bradley, Arwen, Nakkiran, Preetum, Susskind, Joshua, Littwin, Etai
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2310.20703