PDS-1B is a 1B model with
Mistral achitecture pre-trained from scratch on the data selected from the CC split of
Redpajama, using the PDS framework.
The PDS framework is based on the
Pontryagin's maximum principle for optimal pre-training data selection, which not only enjoy strong theoretical support but is also scalable for training large language models.
PDS-selected data improves the performance of language models pre-trained from scratch and saves pre-training comptation. The improvement scales up to large model sizes.
1@article{gu2024data,
2 title={Data Selection via Optimal Control for Language Models},
3 author={Gu, Yuxian and Dong, Li and Wang, Hongning and Hao, Yaru and Dong, Qingxiu and Wei, Furu and Huang, Minlie},
4 journal={arXiv preprint arXiv:2410.07064},
5 year={2024}
6}
