OALL/details_cognitivecomputations__dolphin-2.9.3-mistral-7B-32k

该数据集是在模型`cognitivecomputations/dolphin-2.9.3-mistral-7B-32k`的评估运行过程中自动生成的，包含136个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果作为一个特定的分割（split），分割名称使用运行的时间戳。此外，数据集还包含一个名为`results`的配置，存储了所有运行的聚合结果。README还提供了加载数据集的具体代码示例，并展示了最新的评估结果。

Dataset automatically created during the evaluation run of model cognitivecomputations/dolphin-2.9.3-mistral-7B-32k. It consists of 136 configurations, each corresponding to one of the evaluated tasks. The dataset is derived from a single run, with each run result stored as a specific split named using the timestamp of the run. The train split always points to the latest results, and an additional results configuration stores all the aggregated results of the run. The dataset includes various metrics such as acc_norm, acc_norm_stderr, acc, and acc_stderr for different tasks and communities.