Lansechen/details_Lansechen__Qwen2.5-7B-Open-R1-GRPO-math-lighteval-v2
收藏Hugging Face2025-04-06 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/Lansechen/details_Lansechen__Qwen2.5-7B-Open-R1-GRPO-math-lighteval-v2
下载链接
链接失效反馈官方服务：
资源简介：
在模型Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-v2的评估运行过程中自动创建的数据集，包含三个配置，每个配置对应一个评估任务。数据集包含9次运行的结果，每次运行结果以特定时间戳命名的分割形式存在，train分割指向最新结果。另外，results配置存储所有运行的汇总结果。
Dataset automatically created during the evaluation run of model Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-v2, containing three configurations, each corresponding to one evaluation task. The dataset includes results from nine runs, with each runs results existing as a specific split named with a timestamp, and the train split pointing to the latest results. Additionally, the results configuration stores aggregated results from all runs.
提供机构：
Lansechen
