five

open-llm-leaderboard/details_lgaalves__gpt2_open-platypus

收藏
Hugging Face2023-10-15 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_lgaalves__gpt2_open-platypus
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在评估模型[lgaalves/gpt2_open-platypus](https://huggingface.co/lgaalves/gpt2_open-platypus)时自动生成的,用于在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上进行评估。数据集包含64个配置,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果作为一个特定的分割,分割名称使用运行的时间戳。"train"分割始终指向最新的结果。此外,还有一个名为"results"的配置,存储了所有运行的聚合结果,并用于计算和显示在Open LLM Leaderboard上的聚合指标。

该数据集是在评估模型[lgaalves/gpt2_open-platypus](https://huggingface.co/lgaalves/gpt2_open-platypus)时自动生成的,用于在[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)上进行评估。数据集包含64个配置,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果作为一个特定的分割,分割名称使用运行的时间戳。"train"分割始终指向最新的结果。此外,还有一个名为"results"的配置,存储了所有运行的聚合结果,并用于计算和显示在Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

该数据集是在评估模型 lgaalves/gpt2_open-platypusOpen LLM Leaderboard 上的自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。

数据集结构

数据集由 2 次运行创建,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。

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。

加载数据示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_lgaalves__gpt2_open-platypus", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-15T13:45:26.230063 运行的最新结果: python { "all": { "em": 0.001363255033557047, "em_stderr": 0.00037786091964607695, "f1": 0.04636010906040263, "f1_stderr": 0.0012972722820894797, "acc": 0.25726959447047076, "acc_stderr": 0.007559748871273466 }, "harness|drop|3": { "em": 0.001363255033557047, "em_stderr": 0.00037786091964607695, "f1": 0.04636010906040263, "f1_stderr": 0.0012972722820894797 }, "harness|gsm8k|5": { "acc": 0.001516300227445034, "acc_stderr": 0.0010717793485492632 }, "harness|winogrande|5": { "acc": 0.5130228887134964, "acc_stderr": 0.01404771839399767 } }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|arc:challenge|25_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_drop_3

    • split: 2023_10_15T13_45_26.230063
      • path: **/details_harness|drop|3_2023-10-15T13-45-26.230063.parquet
    • split: latest
      • path: **/details_harness|drop|3_2023-10-15T13-45-26.230063.parquet
  • config_name: harness_gsm8k_5

    • split: 2023_10_15T13_45_26.230063
      • path: **/details_harness|gsm8k|5_2023-10-15T13-45-26.230063.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2023-10-15T13-45-26.230063.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hellaswag|10_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_08_31T17_11_08.445217
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-management|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-security_studies|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-sociology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-virology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-world_religions|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-management|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-security_studies|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-sociology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-virology|5_2023-08-31T17:11:08.445217.parquet
        • **/details_harness|hendrycksTest-world_religions|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_abstract_algebra_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_anatomy_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-anatomy|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-anatomy|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_astronomy_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-astronomy|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-astronomy|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_business_ethics_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-business_ethics|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-business_ethics|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_clinical_knowledge_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_college_biology_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-college_biology|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-college_biology|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_college_chemistry_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-college_chemistry|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-college_chemistry|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_college_computer_science_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-college_computer_science|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-college_computer_science|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_college_mathematics_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-college_mathematics|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-college_mathematics|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_college_medicine_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-college_medicine|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-college_medicine|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_college_physics_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-college_physics|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-college_physics|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_computer_security_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-computer_security|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-computer_security|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_conceptual_physics_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_econometrics_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-econometrics|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-econometrics|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_electrical_engineering_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-31T17:11:08.445217.parquet
  • config_name: harness_hendrycksTest_elementary_mathematics_5

    • split: 2023_08_31T17_11_08.445217
      • path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-31T17:11:08.445217.parquet
    • split: latest
      • path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-31T17:11:08.445217.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