OALL/details_Qwen__Qwen3-8B-Base_v2

该数据集是在对Qwen/Qwen3-8B-Base模型进行评估时自动创建的。数据集由116个配置组成，每个配置对应一个评估任务。数据集是从一次运行中创建的，每次运行都可以在各个配置中找到，配置的名称使用运行的timestamp。train分割总是指向最新的结果。还有一个额外的配置results存储了运行的所有聚合结果。README文件还包括一个代码片段，演示了如何使用datasets模块中的load_dataset函数加载数据的详细信息。最后，README提供了来自特定运行的最新结果，包括各种任务的准确性和标准误差。

This dataset was automatically created during the evaluation run of the Qwen/Qwen3-8B-Base model. The dataset consists of 116 configurations, each corresponding to one of the evaluated tasks. The dataset is derived from one run, with each run being split into different configurations named by the timestamp of the run. The train split always points to the latest results. An additional configuration results stores all the aggregated results of the run. The README file also includes a code snippet demonstrating how to load details from a run using the load_dataset function from the datasets module. Lastly, the README provides the latest results from a specific run, including accuracy and standard error for various tasks.