OALL/details_deep-analysis-research__D2IL-Arabic-Qwen2.5-72B-Instruct-v0.1_v2

该数据集是在模型 deep-analysis-research/D2IL-Arabic-Qwen2.5-72B-Instruct-v0.1 的评估运行过程中自动创建的。数据集由 116 个配置组成，每个配置对应一个评估任务。数据集由 1 次运行创建，每次运行都作为一个特定的分割存储，分割名称使用运行的 timestamp。train 分割总是指向最新的结果。此外，还有一个额外的配置 results 存储运行的所有聚合结果。README 还提供了一个使用 Python 和 datasets 库加载数据运行详情的示例。最后，README 包含了特定运行的最新结果，显示了各种任务的准确性和标准误差。

Dataset automatically created during the evaluation run of the model deep-analysis-research/D2IL-Arabic-Qwen2.5-72B-Instruct-v0.1. The dataset consists of 116 configurations, each corresponding to an evaluated task. The dataset has been created from 1 run and each run is stored as a specific split named with the timestamp of the run. The train split always points to the latest results. There is also an additional configuration results that stores all the aggregated results of the run. The README also provides an example of how to load the details from a run using Python and the datasets library. Lastly, the README includes the latest results from a specific run, showing the accuracy and standard error for various tasks.