OALL/details_MaziyarPanahi__Qwen2-72B-Instruct-v0.1
收藏Hugging Face2024-07-19 更新2024-07-22 收录
下载链接:
https://hf-mirror.com/datasets/OALL/details_MaziyarPanahi__Qwen2-72B-Instruct-v0.1
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MaziyarPanahi/Qwen2-72B-Instruct-v0.1期间自动创建的。它包含136个配置,每个配置对应一个评估任务。数据集来自一次运行,每次运行以运行时间戳命名的分割形式存在。train分割始终指向最新的结果。此外,还有一个results配置,汇总了所有运行的结果。数据集详细记录了各项任务的准确性指标。
Dataset automatically created during the evaluation run of model [MaziyarPanahi/Qwen2-72B-Instruct-v0.1]. It consists of 136 configurations, each corresponding to an evaluated task. The dataset has been created from 1 run, with each run represented as a split named using the timestamp of the run. The train split always points to the latest results. An additional results configuration stores all the aggregated results of the run. The dataset is detailed with specific accuracy metrics for various tasks.
提供机构:
OALL
原始信息汇总
数据集概述
数据集基本信息
- 名称: Evaluation run of MaziyarPanahi/Qwen2-72B-Instruct-v0.1
- 来源: 自动创建于模型评估运行期间
- 配置数量: 136
- 创建次数: 1次
数据集结构
- 配置: 每个配置对应一个评估任务
- 分割: 每个运行结果作为一个特定的分割,分割名称使用运行的时间戳
- 训练分割: 指向最新的结果
- 结果配置: 存储所有运行的聚合结果
最新结果
- 时间戳: 2024-07-19T23:46:18.034290
- 结果: 包含多个任务的准确率和标准误差
示例代码
python from datasets import load_dataset data = load_dataset("OALL/details_MaziyarPanahi__Qwen2-72B-Instruct-v0.1", "lighteval_xstory_cloze_ar_0", split="train")



