OALL/details_cognitivecomputations__Dolphin3.0-R1-Mistral-24B_v2

这是一个在评估模型 [cognitivecomputations/Dolphin3.0-R1-Mistral-24B](https://huggingface.co/cognitivecomputations/Dolphin3.0-R1-Mistral-24B) 时自动创建的数据集。数据集包含116个配置，每个配置对应一个评估任务。数据集由1次运行创建，每次运行可以作为每个配置中的特定分割找到，分割名称使用运行的timestamp命名。train分割始终指向最新结果。还有一个额外的配置results存储了所有运行的汇总结果。文件还包含了一个使用Python中的datasets库从运行中加载数据的示例。

Dataset automatically created during the evaluation run of model [cognitivecomputations/Dolphin3.0-R1-Mistral-24B](https://huggingface.co/cognitivecomputations/Dolphin3.0-R1-Mistral-24B). The dataset consists of 116 configurations, each corresponding to one of the evaluated tasks. The dataset is created from 1 run(s), and each run can be found as a specific split in each configuration, named using 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 file also includes an example of how to load the details from a run using the datasets library in Python.