open-llm-leaderboard/details_Sao10K__Frostwind-v2.1-m7
收藏Hugging Face2024-03-13 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Sao10K__Frostwind-v2.1-m7
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在模型Sao10K/Frostwind-v2.1-m7的评估运行期间自动创建的,用于Open LLM排行榜。数据集包含63个配置,每个配置对应一个评估任务。数据集来源于1次运行,每次运行都以运行时间戳命名的特定分割形式存在。train分割始终指向最新结果。此外,results配置存储了运行的所有聚合结果,用于在排行榜上计算和显示聚合指标。数据集针对不同任务有特定的配置,并包含每个任务的详细指标,如准确率和标准误差。
该数据集是在模型Sao10K/Frostwind-v2.1-m7的评估运行期间自动创建的,用于Open LLM排行榜。数据集包含63个配置,每个配置对应一个评估任务。数据集来源于1次运行,每次运行都以运行时间戳命名的特定分割形式存在。train分割始终指向最新结果。此外,results配置存储了运行的所有聚合结果,用于在排行榜上计算和显示聚合指标。数据集针对不同任务有特定的配置,并包含每个任务的详细指标,如准确率和标准误差。
提供机构:
open-llm-leaderboard
原始信息汇总
数据集概述
数据集名称
- pretty_name: Evaluation run of Sao10K/Frostwind-v2.1-m7
数据集创建
- dataset_summary: 该数据集是在评估模型Sao10K/Frostwind-v2.1-m7的过程中自动创建的,评估平台为Open LLM Leaderboard。
数据集组成
- 配置数量: 63个
- 每个配置对应任务: 每个配置对应一个评估任务
- 数据集来源: 数据集由1次运行创建,每次运行对应一个特定的分割,分割名称使用运行的时间戳命名。
- 额外配置: 存在一个名为"results"的配置,用于存储所有聚合的运行结果,用于计算和显示聚合指标。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Sao10K__Frostwind-v2.1-m7", "harness_winogrande_5", split="train")
最新结果
- 结果来源: 最新结果来自run 2024-03-13T18:05:13.831443。
数据集配置详情
配置列表
- harness_arc_challenge_25
- 数据文件路径:
- split: 2024_03_13T18_05_13.831443
- path: **/details_harness|arc:challenge|25_2024-03-13T18-05-13.831443.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-03-13T18-05-13.831443.parquet
- split: 2024_03_13T18_05_13.831443
- 数据文件路径:
- harness_gsm8k_5
- 数据文件路径:
- split: 2024_03_13T18_05_13.831443
- path: **/details_harness|gsm8k|5_2024-03-13T18-05-13.831443.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-03-13T18-05-13.831443.parquet
- split: 2024_03_13T18_05_13.831443
- 数据文件路径:
- harness_hellaswag_10
- 数据文件路径:
- split: 2024_03_13T18_05_13.831443
- path: **/details_harness|hellaswag|10_2024-03-13T18-05-13.831443.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-03-13T18-05-13.831443.parquet
- split: 2024_03_13T18_05_13.831443
- 数据文件路径:
- harness_hendrycksTest_5
- 数据文件路径:
- split: 2024_03_13T18_05_13.831443
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-management|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-virology|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-03-13T18-05-13.831443.parquet
- path:
- split: latest
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-13T18-05-13.831443.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-13T18-
- path:
- split: 2024_03_13T18_05_13.831443
- 数据文件路径:



