five

open-llm-leaderboard-old/details_aiplanet__panda-coder-13B

收藏
Hugging Face2023-12-03 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_aiplanet__panda-coder-13B
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aiplanet/panda-coder-13B时自动创建的,由64个配置组成,每个配置对应一个评估任务。数据集由3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aiplanet/panda-coder-13B时自动创建的,由64个配置组成,每个配置对应一个评估任务。数据集由3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-old
原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型 aiplanet/panda-coder-13BOpen LLM Leaderboard 上的运行过程中自动创建的。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 3 次运行结果组成,每次运行的结果可以在每个配置中找到,并以运行的时间戳命名。"train" 分割总是指向最新的结果。

额外配置

有一个额外的配置 "results",存储所有运行的聚合结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标。

数据加载示例

以下是加载特定运行详细信息的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_aiplanet__panda-coder-13B", "harness_gsm8k_5", split="train")

最新结果

以下是 2023-12-03T22:12:43.362775 运行的最新结果: python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }

配置详情

数据集包含多个配置,每个配置对应不同的任务和运行结果。以下是部分配置的详细信息:

配置列表

  • harness_arc_challenge_25

    • 分割: 2023_10_04T16_56_18.723336
      • 路径: **/details_harness|arc:challenge|25_2023-10-04T16-56-18.723336.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2023-10-04T16-56-18.723336.parquet
  • harness_drop_3

    • 分割: 2023_11_08T14_53_54.622402
      • 路径: **/details_harness|drop|3_2023-11-08T14-53-54.622402.parquet
    • 分割: latest
      • 路径: **/details_harness|drop|3_2023-11-08T14-53-54.622402.parquet
  • harness_gsm8k_5

    • 分割: 2023_11_08T14_53_54.622402
      • 路径: **/details_harness|gsm8k|5_2023-11-08T14-53-54.622402.parquet
    • 分割: 2023_12_03T22_12_43.362775
      • 路径: **/details_harness|gsm8k|5_2023-12-03T22-12-43.362775.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2023-12-03T22-12-43.362775.parquet
  • harness_hellaswag_10

    • 分割: 2023_10_04T16_56_18.723336
      • 路径: **/details_harness|hellaswag|10_2023-10-04T16-56-18.723336.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2023-10-04T16-56-18.723336.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_10_04T16_56_18.723336
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-management|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-security_studies|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-sociology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-virology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-world_religions|5_2023-10-04T16-56-18.723336.parquet
    • 分割: latest
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-management|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-security_studies|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-sociology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-virology|5_2023-10-04T16-56-18.723336.parquet
        • **/details_harness|hendrycksTest-world_religions|5_2023-10-04T16-56-18.723336.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