CMR Scaling Law

The dataset used in the paper is a mixture of general corpus and domain-specific corpus, with a power-law relationship between loss, mixture ratio, and training tokens scale.

Data and Resources

Cite this as

Jiawei Gu, Zacc Yang, Chuanghao Ding, Rui Zhao, Fei Tan (2025). Dataset: CMR Scaling Law. https://doi.org/10.57702/8vx49sro

DOI retrieved: January 2, 2025

Additional Info

Field Value
Created January 2, 2025
Last update January 2, 2025
Defined In https://doi.org/10.48550/arXiv.2407.17467
Author Jiawei Gu
More Authors
Zacc Yang
Chuanghao Ding
Rui Zhao
Fei Tan