CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models

@inproceedings{gu2024scaling,
  title = {CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models},
  author = {Jiawei Gu and Zacc Yang and Chuanghao Ding and Rui Zhao and Fei Tan},
  year = {2024},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  eprint = {2407.17467},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.17467},
}