OALL/details_oddadmix__Arabic-Qwen2.5-3B

该数据集是在评估模型 oddadmix/Arabic-Qwen2.5-3B 时自动创建的。数据集由 136 个配置组成，每个配置对应一个评估任务。数据集包括来自一次运行的结果，每个运行都有一个特定的分割，分割的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 的额外配置，存储了所有运行的综合结果。README 还包括使用 Python 和 datasets 库加载数据集细节的示例，以及特定运行时间戳的最新结果。

Dataset automatically created during the evaluation run of model [oddadmix/Arabic-Qwen2.5-3B](https://huggingface.co/oddadmix/Arabic-Qwen2.5-3B). The dataset is composed of 136 configurations, each one corresponding to one of the evaluated tasks. The dataset includes results from one run, with each run having a specific split named by the timestamp. The train split always points to the latest results. Additionally, theres an extra configuration results storing all aggregated results of the run. The README also includes examples on how to load the dataset details using Python and the datasets library, as well as the latest results from a specific run timestamp.