OALL/details_Qwen__Qwen2.5-Coder-14B-Instruct

该数据集是在模型Qwen/Qwen2.5-Coder-14B-Instruct的评估运行期间自动创建的。数据集由136个配置组成，每个配置对应一个评估任务。数据集是从1次运行中生成的，每次运行都作为每个配置中的一个特定分割存储，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，存储了所有运行的聚合结果。README还提供了如何使用Hugging Face datasets库加载数据集的示例。

The dataset is automatically created during the evaluation run of the model Qwen/Qwen2.5-Coder-14B-Instruct. It consists of 136 configurations, each corresponding to one of the evaluated tasks. The dataset is generated from one run, with each run represented as a specific split 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 dataset includes various tasks related to Arabic culture, history, and other domains, with each task having its own accuracy metrics and standard errors.