This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used in the DeepSeek-R1 series, we develop an alternative approach leveraging exclusively public data and models. Our curriculum training progressively increases data difficulty, combined with multi-staged post-training. Our Light-R1-32B model, trained from Qwen2.5-32B-Instruct, outperforms DeepSeek-R1-Distill-Qwen-32B in math reasoning. Experimental results show that this curriculum approach becomes more effective when distinct, diverse datasets are available for different training stages: fine-tuning DeepSeek-R1-Distilled models (pre-tuned by DeepSeek team on proprietary data) with 3,000 challenging examples from our curriculum dataset yielded state-of-the-art 7B and 14B models, while the 32B model, Light-R1-32B-DS performed comparably to QwQ-32B and DeepSeek-R1. Furthermore, we extend our work by applying GRPO on long reasoning models. Our final Light-R1-14B-DS achieves SOTA performance among 14B models in math, with AIME24 \& 25 scores of 74.0 and 60.2 respectively, surpassing many 32B models and DeepSeek-R1-Distill-Llama-70B. Despite math-focused training, Light-R1-14B-DS demonstrates strong cross-domain generalization. Light-R1 represents a significant advancement in making sophisticated reasoning models more accessible and implementable in real-world applications. Our models, training data and code have been made available at https://github.com/Qihoo360/Light-R1.

翻译：本文介绍Light-R1，一个使用可复现且经济高效的方法训练长推理模型的开源套件。鉴于DeepSeek-R1系列所使用的数据具有专有性质，我们开发了一种完全利用公开数据和模型的替代方案。我们的课程式训练逐步增加数据难度，并结合多阶段的后训练。我们从Qwen2.5-32B-Instruct训练得到的Light-R1-32B模型，在数学推理上超越了DeepSeek-R1-Distill-Qwen-32B。实验结果表明，当能为不同训练阶段提供独特且多样化的数据集时，这种课程式方法更为有效：使用我们课程数据集中3000个具有挑战性的示例对DeepSeek-R1-Distilled模型（由DeepSeek团队在其专有数据上预调优）进行微调，产生了最先进的7B和14B模型，而32B模型Light-R1-32B-DS的表现与QwQ-32B和DeepSeek-R1相当。此外，我们通过将GRPO应用于长推理模型来扩展我们的工作。我们最终的Light-R1-14B-DS在14B模型的数学能力上达到了SOTA水平，其AIME24和AIME25得分分别为74.0和60.2，超越了许多32B模型以及DeepSeek-R1-Distill-Llama-70B。尽管训练侧重于数学，Light-R1-14B-DS展现出强大的跨领域泛化能力。Light-R1代表了在使复杂推理模型更易于获取并能在实际应用中实施方面的重要进展。我们的模型、训练数据和代码已在 https://github.com/Qihoo360/Light-R1 公开。