richmondsin/mmlu_id_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。

The dataset was automatically created during the evaluation run of the model google/gemma-2-2b. The dataset is composed of configurations corresponding to evaluated tasks, with each run represented as a split named by the runs timestamp. The train split always points to the latest results. An additional results configuration stores all the aggregated results of the runs. The dataset is used to store evaluation results and can be loaded using the Hugging Face datasets library. The README also includes the latest results from a specific run, showing accuracy metrics for a task named m_mmlu_id. However, detailed descriptions about the datasets source, language, license, and other attributes are marked as More Information Needed, indicating that these details are not provided in the README.