taresco/details_meta-llama__Llama-3.1-70B-Instruct

这是一个在评估模型 meta-llama/Llama-3.1-70B-Instruct 时自动创建的数据集。数据集由7个配置组成，每个配置对应一个评估任务。数据集由7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。还有一个额外的配置results，用于存储所有运行的聚合结果。可以使用提供的Python代码片段来加载数据集的详细信息。

Dataset automatically created during the evaluation run of model [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct). The dataset is composed of 7 configurations, each one corresponding to one of the evaluated tasks. It includes 7 runs, each with a specific split named by the timestamp. The train split always points to the latest results. There is also a results configuration that stores aggregated results of all runs. The dataset can be loaded using the provided Python code snippet.