five

open-llm-leaderboard-old/details_NLPark__Test1_SLIDE

收藏
Hugging Face2024-04-21 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_NLPark__Test1_SLIDE
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型NLPark/Test1_SLIDE进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割名称使用运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在Open LLM Leaderboard上对模型NLPark/Test1_SLIDE进行评估时自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割名称使用运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,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

数据集信息

  • 名称: Evaluation run of NLPark/Test1_SLIDE
  • 来源: 自动创建于模型 NLPark/Test1_SLIDEOpen LLM Leaderboard 的评估运行。
  • 组成: 包含63个配置,每个配置对应一个评估任务。
  • 创建: 从1次运行中创建,每个运行在每个配置中作为一个特定的分割存在,分割名称为运行的时间戳。"train" 分割总是指向最新的结果。
  • 额外配置: "results" 配置存储所有运行的聚合结果,用于计算和显示 Open LLM Leaderboard 上的聚合指标。

最新结果

  • 最新结果: 来自2024-04-21T05:54:07.776692的运行结果,包含多个任务的详细评估指标。

配置详情

  • 配置名称: harness_arc_challenge_25

    • 数据文件:
      • 分割: 2024_04_21T05_54_07.776692
        • 路径: **/details_harness|arc:challenge|25_2024-04-21T05-54-07.776692.parquet
      • 分割: latest
        • 路径: **/details_harness|arc:challenge|25_2024-04-21T05-54-07.776692.parquet
  • 配置名称: harness_gsm8k_5

    • 数据文件:
      • 分割: 2024_04_21T05_54_07.776692
        • 路径: **/details_harness|gsm8k|5_2024-04-21T05-54-07.776692.parquet
      • 分割: latest
        • 路径: **/details_harness|gsm8k|5_2024-04-21T05-54-07.776692.parquet
  • 配置名称: harness_hellaswag_10

    • 数据文件:
      • 分割: 2024_04_21T05_54_07.776692
        • 路径: **/details_harness|hellaswag|10_2024-04-21T05-54-07.776692.parquet
      • 分割: latest
        • 路径: **/details_harness|hellaswag|10_2024-04-21T05-54-07.776692.parquet
  • 配置名称: harness_hendrycksTest_5

    • 数据文件:
      • 分割: 2024_04_21T05_54_07.776692
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-international_law|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-management|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-marketing|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-professional_law|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-professional_medicine|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-professional_psychology|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-public_relations|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-security_studies|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-sociology|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-us_foreign_policy|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-virology|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-world_religions|5_2024-04-21T05-54-07.776692.parquet
      • 分割: latest
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-21T05-54-07.776692.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-0
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