richmondsin/arc_zh_results

该数据集是在评估模型google/gemma-2-2b时自动创建的。数据集由0个配置组成，每个配置对应一个评估任务。数据集由2次运行创建，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，还有一个名为results的配置存储所有运行的聚合结果。文件中还提供了加载数据集的方法示例，并展示了最新的评估结果。

The dataset was automatically created during the evaluation run of the model google/gemma-2-2b. The dataset consists of 0 configurations, each corresponding to an evaluated task. The dataset was created from 2 runs, with each run stored as a specific split named by the runs timestamp. The train split always points to the latest results. An additional configuration results stores all aggregated results of the runs. Specific run details can be loaded using the Hugging Face datasets library. The latest results include accuracy metrics for a task named arc_zh.