five

open-llm-leaderboard-old/details_janhq__supermario-v1

收藏
Hugging Face2023-12-12 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_janhq__supermario-v1
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janhq/supermario-v1在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集来源于一次运行,每个运行以运行的时间戳命名,作为特定分割。train分割始终指向最新的结果,而额外的results配置存储了用于在Leaderboard上计算和显示聚合指标的所有聚合结果。此外,README文件中还包含了一个用于加载运行详细信息的Python代码示例。

该数据集是在模型janhq/supermario-v1在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集来源于一次运行,每个运行以运行的时间戳命名,作为特定分割。train分割始终指向最新的结果,而额外的results配置存储了用于在Leaderboard上计算和显示聚合指标的所有聚合结果。此外,README文件中还包含了一个用于加载运行详细信息的Python代码示例。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集名称

  • 名称: Evaluation run of janhq/supermario-v1

数据集组成

  • 配置数量: 63个配置
  • 每个配置对应: 一个评估任务
  • 创建来源: 从1次运行中创建
  • 分割命名: 使用运行的时间戳命名
  • 训练分割: 始终指向最新结果
  • 额外配置: "results"存储所有聚合结果,用于计算和显示在Open LLM Leaderboard上的聚合指标

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_janhq__supermario-v1", "harness_winogrande_5", split="train")

最新结果

  • 结果来源: 2023-12-12T03:51:54.393256
  • 详细结果: 包含多个任务的准确率(acc)、标准化准确率(acc_norm)、误差(stderr)等指标

配置详情

  • 配置名称: harness_arc_challenge_25

    • 数据文件:
      • 分割: 2023_12_12T03_51_54.393256
        • 路径: **/details_harness|arc:challenge|25_2023-12-12T03-51-54.393256.parquet
      • 分割: latest
        • 路径: **/details_harness|arc:challenge|25_2023-12-12T03-51-54.393256.parquet
  • 配置名称: harness_gsm8k_5

    • 数据文件:
      • 分割: 2023_12_12T03_51_54.393256
        • 路径: **/details_harness|gsm8k|5_2023-12-12T03-51-54.393256.parquet
      • 分割: latest
        • 路径: **/details_harness|gsm8k|5_2023-12-12T03-51-54.393256.parquet
  • 配置名称: harness_hellaswag_10

    • 数据文件:
      • 分割: 2023_12_12T03_51_54.393256
        • 路径: **/details_harness|hellaswag|10_2023-12-12T03-51-54.393256.parquet
      • 分割: latest
        • 路径: **/details_harness|hellaswag|10_2023-12-12T03-51-54.393256.parquet
  • 配置名称: harness_hendrycksTest_5

    • 数据文件:
      • 分割: 2023_12_12T03_51_54.393256
        • 路径:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-international_law|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-management|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-marketing|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-professional_law|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-professional_medicine|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-professional_psychology|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-public_relations|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-security_studies|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-sociology|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-virology|5_2023-12-12T03-51-54.393256.parquet
          • **/details_harness|hendrycksTest-world_religions|5_2023-12-12T03-51-54.393256.parquet
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