OALL/details_TIGER-Lab__MAmmoTH2-8B-Plus
收藏Hugging Face2024-06-17 更新2024-06-29 收录
下载链接:
https://hf-mirror.com/datasets/OALL/details_TIGER-Lab__MAmmoTH2-8B-Plus
下载链接
链接失效反馈官方服务:
资源简介:
数据集TIGER-Lab/MAmmoTH2-8B-Plus是在模型评估过程中自动创建的,包含136个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果作为特定的分割存储在配置中,分割名称使用运行的时间戳命名。train分割始终指向最新的结果。此外,还有一个名为results的配置存储了所有运行的聚合结果。
The dataset TIGER-Lab/MAmmoTH2-8B-Plus was automatically created during the evaluation run of the model. It consists of 136 configurations, each corresponding to one of the evaluated tasks. The dataset was generated from 1 run, with the results of each run stored as a specific split in each configuration, named using the timestamp of the run. The train split always points to the latest results. Additionally, there is a configuration named results that stores all the aggregated results of the run.
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 TIGER-Lab/MAmmoTH2-8B-Plus
- 来源: 自动创建于模型 TIGER-Lab/MAmmoTH2-8B-Plus 的评估运行过程中。
- 配置数量: 136 个配置,每个配置对应一个评估任务。
- 创建次数: 1 次运行,每次运行结果存储在特定的 split 中,split 名称使用运行的时间戳。
- 额外配置: 包含一个名为 "results" 的配置,存储所有运行结果的聚合。
数据加载示例
python from datasets import load_dataset data = load_dataset("OALL/details_TIGER-Lab__MAmmoTH2-8B-Plus", "lighteval_xstory_cloze_ar_0", split="train")
最新结果
- 最新运行时间: 2024-06-17T08:06:49.280516
- 结果示例: python { "all": { "acc_norm": 0.42476438053086224, "acc_norm_stderr": 0.03762225314205735, "acc": 0.6062210456651225, "acc_stderr": 0.012573415912965187 }, "community|acva:Algeria|0": { "acc_norm": 0.558974358974359, "acc_norm_stderr": 0.0356473293185358 }, ... }



