metadata
license: apache-2.0
datasets:
- gair-prox/open-web-math-pro
language:
- en
base_model:
- mistralai/Mistral-7B-v0.1
pipeline_tag: text-generation
library_name: transformers
Mistral-7B-ProXMath
ArXiv | Data: OpenWebMath-Pro | Code
Mistral-7B-ProXMath is a math-adapted Mistral-7B-v0.1 model that is continually pre-trained on OpenWebMath-Pro (a refined version by ProX) for 10B tokens.
Evaluations
ProX models are evaluated on 9 common math reasoning benchmarks.
| Model | asdiv | gsm8k | mathqa | mawps | minerva_math | mmlu_stem | sat_math | svamp | tabmwp | average |
|---|---|---|---|---|---|---|---|---|---|---|
| Mistral-7B-v0.1 | 68.5 | 40.6 | 32.3 | 87.0 | 11.4 | 50.0 | 56.2 | 65.4 | 52.9 | 51.6 |
| Mistral-7B-ProXMath | 72.9 | 51.0 | 53.0 | 89.2 | 22.4 | 54.2 | 75.0 | 64.9 | 49.8 | 59.2 |
Citation
@article{zhou2024programming,
title={Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale},
author={Zhou, Fan and Wang, Zengzhi and Liu, Qian and Li, Junlong and Liu, Pengfei},
journal={arXiv preprint arXiv:2409.17115},
year={2024}
}