Lansechen/details_Lansechen__Qwen2.5-7B-Open-R1-GRPO-math-lighteval
收藏Hugging Face2025-04-10 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
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评估过程中自动生成的数据集，包含5种配置，每种配置对应一个评估任务。该数据集由23次运行结果组成，每次运行结果在各个配置中作为特定分割存在，分割名称以运行时间戳命名。train 分割指向最新运行结果，而results 配置则存储了所有运行的汇总结果。
A dataset automatically created during the evaluation of the model Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval, containing 5 configurations, each corresponding to an evaluation task. The dataset is composed of results from 23 runs, with each run represented as a specific split in each configuration, named using the timestamp of the run. The train split always points to the latest results, while the results configuration stores aggregated results from all runs.
提供机构：
Lansechen
