OALL/details_oddadmix__Arabic-Qwen2.5-3B-v2

该数据集是在评估模型 [oddadmix/Arabic-Qwen2.5-3B-v2](https://huggingface.co/oddadmix/Arabic-Qwen2.5-3B-v2) 的过程中自动生成的。数据集由 136 个配置组成，每个配置对应一个评估任务。数据集由 1 次运行创建，每次运行的每个配置都有一个特定的分割，分割名称使用运行的时间戳命名。"train" 分割始终指向最新的结果。此外，还有一个额外的配置 "results" 存储所有运行的汇总结果。README 包含一个 Python 代码片段，用于从运行中加载详细信息。它还提供了特定运行时间戳为 2024-12-28T09:40:47.829708 的最新结果。

The dataset was automatically created during the evaluation run of the model [oddadmix/Arabic-Qwen2.5-3B-v2](https://huggingface.co/oddadmix/Arabic-Qwen2.5-3B-v2). The dataset consists of 136 configurations, each corresponding to one of the evaluated tasks. It has been created from 1 run, with each runs results split and named using 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 includes a Python code snippet for loading the details from a run. It also provides the latest results from a specific run timestamped on 2024-12-28T09:40:47.829708.