Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912033835843584 |
|---|---|
| author | Yang, An Zhang, Beichen Hui, Binyuan Gao, Bofei Yu, Bowen Li, Chengpeng Liu, Dayiheng Tu, Jianhong Zhou, Jingren Lin, Junyang Lu, Keming Xue, Mingfeng Lin, Runji Liu, Tianyu Ren, Xingzhang Zhang, Zhenru |
| author_facet | Yang, An Zhang, Beichen Hui, Binyuan Gao, Bofei Yu, Bowen Li, Chengpeng Liu, Dayiheng Tu, Jianhong Zhou, Jingren Lin, Junyang Lu, Keming Xue, Mingfeng Lin, Runji Liu, Tianyu Ren, Xingzhang Zhang, Zhenru |
| contents | In this report, we present a series of math-specific large language models: Qwen2.5-Math and Qwen2.5-Math-Instruct-1.5B/7B/72B. The core innovation of the Qwen2.5 series lies in integrating the philosophy of self-improvement throughout the entire pipeline, from pre-training and post-training to inference: (1) During the pre-training phase, Qwen2-Math-Instruct is utilized to generate large-scale, high-quality mathematical data. (2) In the post-training phase, we develop a reward model (RM) by conducting massive sampling from Qwen2-Math-Instruct. This RM is then applied to the iterative evolution of data in supervised fine-tuning (SFT). With a stronger SFT model, it's possible to iteratively train and update the RM, which in turn guides the next round of SFT data iteration. On the final SFT model, we employ the ultimate RM for reinforcement learning, resulting in the Qwen2.5-Math-Instruct. (3) Furthermore, during the inference stage, the RM is used to guide sampling, optimizing the model's performance.
Qwen2.5-Math-Instruct supports both Chinese and English, and possess advanced mathematical reasoning capabilities, including Chain-of-Thought (CoT) and Tool-Integrated Reasoning (TIR). We evaluate our models on 10 mathematics datasets in both English and Chinese, such as GSM8K, MATH, GaoKao, AMC23, and AIME24, covering a range of difficulties from grade school level to math competition problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12122 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement Yang, An Zhang, Beichen Hui, Binyuan Gao, Bofei Yu, Bowen Li, Chengpeng Liu, Dayiheng Tu, Jianhong Zhou, Jingren Lin, Junyang Lu, Keming Xue, Mingfeng Lin, Runji Liu, Tianyu Ren, Xingzhang Zhang, Zhenru Computation and Language Artificial Intelligence Machine Learning In this report, we present a series of math-specific large language models: Qwen2.5-Math and Qwen2.5-Math-Instruct-1.5B/7B/72B. The core innovation of the Qwen2.5 series lies in integrating the philosophy of self-improvement throughout the entire pipeline, from pre-training and post-training to inference: (1) During the pre-training phase, Qwen2-Math-Instruct is utilized to generate large-scale, high-quality mathematical data. (2) In the post-training phase, we develop a reward model (RM) by conducting massive sampling from Qwen2-Math-Instruct. This RM is then applied to the iterative evolution of data in supervised fine-tuning (SFT). With a stronger SFT model, it's possible to iteratively train and update the RM, which in turn guides the next round of SFT data iteration. On the final SFT model, we employ the ultimate RM for reinforcement learning, resulting in the Qwen2.5-Math-Instruct. (3) Furthermore, during the inference stage, the RM is used to guide sampling, optimizing the model's performance. Qwen2.5-Math-Instruct supports both Chinese and English, and possess advanced mathematical reasoning capabilities, including Chain-of-Thought (CoT) and Tool-Integrated Reasoning (TIR). We evaluate our models on 10 mathematics datasets in both English and Chinese, such as GSM8K, MATH, GaoKao, AMC23, and AIME24, covering a range of difficulties from grade school level to math competition problems. |
| title | Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2409.12122 |