five

Lansechen/details_Lansechen__Qwen2.5-7B-Open-R1-GRPO-math-lighteval-cosine

收藏
Hugging Face2025-04-07 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-cosine
下载链接
链接失效反馈
官方服务:
资源简介:
在评估模型Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-cosine时自动创建的数据集,包含3种配置,每种配置对应一个评估任务。数据集由9次运行的结果组成,每次运行结果在各自的配置中以时间戳命名的分割中存储,train分割指向最新结果,results配置存储所有运行的汇总结果。

Dataset automatically created during the evaluation of model Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-cosine, containing 3 configurations, each corresponding to one evaluation task. The dataset is composed of results from 9 runs, with each runs results stored in a timestamp-named split within its respective configuration, the train split pointing to the latest results, and the results configuration storing aggregated results from all runs.
提供机构:
Lansechen
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作