taresco/details_taresco__llama3instruct_no_instruction_mask_40k

在模型taresco/llama3instruct_no_instruction_mask_40k的评估运行过程中自动创建的数据集。包含18个配置，每个配置对应于一个评估任务。数据集由22次运行创建，每次运行在每个配置中都有一个特定的分割，分割的名称使用运行的timestamp。"train"分割始终指向最新的结果。此外，还有一个配置"results"用于存储所有运行的聚合结果。

Dataset automatically created during the evaluation run of model taresco/llama3instruct_no_instruction_mask_40k. It consists of 18 configurations, each corresponding to one evaluation task. The dataset is created from 22 runs, with each run having a specific split in each configuration, named using the runs timestamp. The "train" split always points to the latest results. Additionally, there is a configuration "results" that stores the aggregated results of all runs.