OALL/details_Qwen__Qwen3-4B-Instruct-2507_v2

这个数据集是在评估模型Qwen/Qwen3-4B-Instruct-2507期间自动创建的。数据集由116个配置组成，每个配置对应一个评估任务。它包括多个运行的成果，每个运行都存储为一个特定的分割，分割名称使用运行的日期时间戳。train分割始终指向最新的结果。还有一个额外的配置results存储所有聚合的结果。可以使用Python中的datasets库加载数据集，如提供的示例所示。README还包含了特定运行的最新结果的详细信息，展示了各种任务的准确性和标准误差。

Dataset automatically created during the evaluation run of model Qwen/Qwen3-4B-Instruct-2507. The dataset consists of 116 configurations, each corresponding to an evaluated task. It includes results from multiple runs, each stored as a specific split named by the timestamp of the run. The train split always points to the latest results. An additional configuration results stores all aggregated results. The dataset can be loaded using the datasets library in Python, as shown in the provided example. The README also includes details about the latest results from a specific run, showcasing the accuracy and standard error for various tasks.