open-llm-leaderboard-old/details_kunkun666__kunkun_dat
收藏Hugging Face2024-04-11 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_kunkun666__kunkun_dat
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kunkun666/kunkun_dat的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集由63个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行都作为每个配置中的一个特定分割,分割名称使用运行的时间戳。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,并用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在模型kunkun666/kunkun_dat的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集由63个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行都作为每个配置中的一个特定分割,分割名称使用运行的时间戳。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,并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总
数据集概述
数据集摘要
该数据集是在评估模型 kunkun666/kunkun_dat 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。数据集从 2 次运行中创建,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
数据集结构
数据集包含多个配置,每个配置对应不同的评估任务。以下是部分配置的详细信息:
配置示例
-
config_name: harness_arc_challenge_25
- data_files:
- split: 2024_04_11T07_46_27.384850
- path: **/details_harness|arc:challenge|25_2024-04-11T07-46-27.384850.parquet
- split: 2024_04_11T07_50_43.081174
- path: **/details_harness|arc:challenge|25_2024-04-11T07-50-43.081174.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-04-11T07-50-43.081174.parquet
- split: 2024_04_11T07_46_27.384850
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_04_11T07_46_27.384850
- path: **/details_harness|gsm8k|5_2024-04-11T07-46-27.384850.parquet
- split: 2024_04_11T07_50_43.081174
- path: **/details_harness|gsm8k|5_2024-04-11T07-50-43.081174.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-04-11T07-50-43.081174.parquet
- split: 2024_04_11T07_46_27.384850
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_04_11T07_46_27.384850
- path: **/details_harness|hellaswag|10_2024-04-11T07-46-27.384850.parquet
- split: 2024_04_11T07_50_43.081174
- path: **/details_harness|hellaswag|10_2024-04-11T07-50-43.081174.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-04-11T07-50-43.081174.parquet
- split: 2024_04_11T07_46_27.384850
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_04_11T07_46_27.384850
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-management|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-virology|5_2024-04-11T07-46-27.384850.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-04-11T07-46-27.384850.parquet
- path:
- split: 2024_04_11T07_50_43.081174
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-11T07-50-43.081174.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-04-11T07-50-43.081174
- path:
- split: 2024_04_11T07_46_27.384850
- data_files:



