OALL/details_meta-llama__Llama-3.2-3B-Instruct_v2

这是一个在模型 [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) 评估过程中自动创建的数据集。数据集由 116 个配置组成，每个配置对应一个评估任务。数据集是从一次运行中创建的，每个运行都有特定的分割，分割的名称使用运行的日期时间。train 分割始终指向最新的结果。还有一个额外的配置 results 存储了运行的所有汇总结果。README 文件还包含一个 Python 代码片段，用于从运行中加载数据，以及一个关于特定运行最新结果的章节。

This is a dataset automatically created during the evaluation run of the model [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct). It consists of 116 configurations, each corresponding to one of the evaluated tasks. The dataset is created from one run(s), with each run available as a specific split named using the timestamp of the run. The train split always points to the latest results. An additional configuration results stores all the aggregated results of the run. The README also includes a Python code snippet for loading details from a run, as well as a section on the latest results from a specific run.