OALL/details_Qwen__Qwen3-32B_v2_alrage

这是一个在评估模型Qwen/Qwen3-32B时自动创建的数据集。数据集包含一个配置，每个配置对应于一个评估任务。数据集由两次运行的结果组成，每次运行都作为一个特定的时间戳命名的拆分存储在配置中。此外，还有一个额外的配置用来存储所有运行聚合的结果。

This dataset was automatically created during the evaluation of the model Qwen/Qwen3-32B. It consists of one configuration, each corresponding to an evaluated task. The dataset is composed of the results from two runs, with each run stored as a specific split named after a timestamp. Additionally, there is an extra configuration for storing the aggregated results of all runs.