ljvmiranda921/details_msde-allenai_Olmo-3-1025-7B-lora-4bit-msde-S1-id_gpt-4o-mini-2024-07-18

该数据集是在模型ljvmiranda921/msde-sft-dev的评估运行期间自动创建的，包含14个配置，每个配置对应一个评估任务。数据集由14次运行组成，每次运行作为特定分割存储在配置中，分割名称使用运行的时间戳。train分割始终指向最新结果。额外的results配置存储了所有运行的聚合结果。数据集用于存储评估细节，并提供了加载数据的示例。还包括了特定运行的最新结果，展示了各种准确性指标。

Dataset automatically created during the evaluation run of model ljvmiranda921/msde-sft-dev. It is composed of 14 configurations, each corresponding to one of the evaluated tasks. The dataset has been created from 14 runs, each stored as a specific split named using the timestamp of the run, with the train split always pointing to the latest results. An additional results configuration stores all the aggregated results of the runs. The dataset is used to store evaluation details, and examples of how to load the data are provided. Latest results from a specific run are also included, showing various accuracy metrics.