five

open-llm-leaderboard-old/details_UCLA-AGI__test-test

收藏
Hugging Face2024-01-06 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_UCLA-AGI__test-test
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UCLA-AGI/test-test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4次运行生成,每次运行的结果作为特定配置中的一个分割,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UCLA-AGI/test-test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4次运行生成,每次运行的结果作为特定配置中的一个分割,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

该数据集是在模型 UCLA-AGI/test-testOpen LLM Leaderboard 上的评估运行期间自动创建的。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 4 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

配置

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2024_01_05T20_55_50.355988
        • path: **/details_harness|arc:challenge|25_2024-01-05T20-55-50.355988.parquet
      • split: 2024_01_05T21_43_53.748756
        • path: **/details_harness|arc:challenge|25_2024-01-05T21-43-53.748756.parquet
      • split: 2024_01_06T00_47_43.486217
        • path: **/details_harness|arc:challenge|25_2024-01-06T00-47-43.486217.parquet
      • split: 2024_01_06T03_24_05.759125
        • path: **/details_harness|arc:challenge|25_2024-01-06T03-24-05.759125.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2024-01-06T03-24-05.759125.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_01_05T20_55_50.355988
        • path: **/details_harness|gsm8k|5_2024-01-05T20-55-50.355988.parquet
      • split: 2024_01_05T21_43_53.748756
        • path: **/details_harness|gsm8k|5_2024-01-05T21-43-53.748756.parquet
      • split: 2024_01_06T00_47_43.486217
        • path: **/details_harness|gsm8k|5_2024-01-06T00-47-43.486217.parquet
      • split: 2024_01_06T03_24_05.759125
        • path: **/details_harness|gsm8k|5_2024-01-06T03-24-05.759125.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2024-01-06T03-24-05.759125.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_01_05T20_55_50.355988
        • path: **/details_harness|hellaswag|10_2024-01-05T20-55-50.355988.parquet
      • split: 2024_01_05T21_43_53.748756
        • path: **/details_harness|hellaswag|10_2024-01-05T21-43-53.748756.parquet
      • split: 2024_01_06T00_47_43.486217
        • path: **/details_harness|hellaswag|10_2024-01-06T00-47-43.486217.parquet
      • split: 2024_01_06T03_24_05.759125
        • path: **/details_harness|hellaswag|10_2024-01-06T03-24-05.759125.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2024-01-06T03-24-05.759125.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_01_05T20_55_50.355988
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-international_law|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-management|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-marketing|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-professional_law|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-professional_medicine|5_2024-01-05T20-55-50.355988.parquet
          • **/details_harness|hendrycksTest-professional_psychology|5_2024-01-05T
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作