OALL/details_AIDC-AI__Marco-LLM-AR_v2

这是一个由模型 [AIDC-AI/Marco-LLM-AR](https://huggingface.co/AIDC-AI/Marco-LLM-AR) 评估运行自动生成的数据集。数据集由116个配置组成，每个配置对应一个评估任务。数据集包括1次运行的结果，每次运行都可以作为特定的时间戳分割来找到，train 分割始终指向最新的结果。此外，results 配置存储了所有运行的综合结果。可以使用 datasets 库和 README 中提供的命令加载数据集。最新的结果也包括在内，展示了各种任务的准确性和标准误差。

Dataset automatically created during the evaluation run of model [AIDC-AI/Marco-LLM-AR](https://huggingface.co/AIDC-AI/Marco-LLM-AR). The dataset is composed of 116 configurations, each corresponding to one of the evaluated tasks. The dataset includes results from 1 run(s), with each run available as a specific split named by the timestamp. The train split always points to the latest results. Additionally, a results configuration stores all aggregated results. The dataset can be loaded using the datasets library with the command provided in the README. The latest results are also included, showing accuracy and standard error for various tasks.