Lansechen/details_Lansechen__Qwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine
收藏数据链接：
官方服务：
资源简介：
在评估模型 Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine 时自动创建的数据集，包含三个配置，每个配置对应一个评估任务。数据集由九次运行构成，每次运行在各个配置中都有命名时间为戳的特定分割，train 始终指向最新结果。另外有一个 results 配置，用于存储所有运行的汇总结果。
Dataset automatically created during the evaluation of the model Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-olympiads-aime-unique-cosine, containing three configurations, each corresponding to one evaluation task. The dataset is composed of nine runs, with each run having a specific split named with the timestamp in each configuration, with train always pointing to the latest results. Additionally, there is a results configuration that stores the aggregated results of all runs.
提供机构：
Lansechen
