taresco/details_gpt-3.5-turbo
收藏Hugging Face2025-11-10 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/taresco/details_gpt-3.5-turbo
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是在评估模型[gpt-3.5-turbo](https://huggingface.co/gpt-3.5-turbo)期间自动创建的。数据集由24个配置组成，每个配置对应一个评估任务。数据集由30次运行创建，每次运行在各自的配置中都有特定的分割，分割的名称使用运行的戳记。"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。要加载运行的详细信息，可以执行以下操作：python
from datasets import load_dataset
data = load_dataset("taresco/details_gpt-3.5-turbo", "results", split="train")
Dataset automatically created during the evaluation run of model [gpt-3.5-turbo](https://huggingface.co/gpt-3.5-turbo). The dataset is composed of 24 configuration, each one corresponding to one of the evaluated task. The dataset has been created from 30 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run. The "train" split is always pointing to the latest results.
提供机构：
taresco
