taresco/details_meta-llama__Llama-3.1-8B-Instruct

该数据集是在评估模型 [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) 时自动创建的。数据集由 28 个配置组成，每个配置对应一个评估任务。数据集由 28 次运行创建，每次运行都可以在每个配置中找到一个特定的分割，分割名称使用运行的 timestamp。train 分割始终指向最新的结果。还有一个额外的配置 results 存储所有运行的综合结果。用户可以使用提供的 Python 代码从运行中加载详细信息。还提供了 2025-04-10T09:14:12.723232 运行的最新结果。

Dataset automatically created during the evaluation run of model [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct). The dataset is composed of 28 configurations, each one corresponding to one of the evaluated tasks. The dataset has been created from 28 runs, with each run represented as a specific split named using the timestamp of the run. There is also an additional configuration results that stores all aggregated results of the runs. Users can load details from a run using Python code provided in the README. The latest results from the run on 2025-04-10T09:14:12.723232 are also provided.