learn.ifs.name

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Shao et al., 2024, DeepSeekMath (arXiv preprint arXiv:2402.03300)

Subscriber deck — free during early access

1 cards in “4.2 Training and Evaluating DeepSeekMath-RL” · whole deck

4.2 Training and Evaluating DeepSeekMath-RL

  1. What did GRPO add on top of DeepSeekMath-Instruct?
    Trained only on about 144K chain-of-thought questions from GSM8K and MATH (64 samples per question), it raised GSM8K from 82.9% to 88.2% and MATH from 46.8% to 51.7%, and also improved out-of-domain benchmarks such as the Chinese CMATH (84.6% → 88.8%).
    • Shao et al., 2024, DeepSeekMath (arXiv preprint arXiv:2402.03300), §4.2

Source

  • Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. In arXiv preprint arXiv:2402.03300. https://arxiv.org/abs/2402.03300