five

open-llm-leaderboard-old/details_NoIdeaLand__test-4k-fn

收藏
Hugging Face2023-10-01 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_NoIdeaLand__test-4k-fn
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NoIdeaLand/test-4k-fn的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集由61个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置中找到,分割以运行的时间戳命名。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,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NoIdeaLand/test-4k-fn的评估运行期间自动创建的,用于Open LLM Leaderboard的评估。数据集由61个配置组成,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置中找到,分割以运行的时间戳命名。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,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

该数据集是在对模型 NoIdeaLand/test-4k-fn 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集组成

  • 数据集包含 61 个配置,每个配置对应一个评估任务。
  • 数据集从 1 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。
  • 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 Open LLM Leaderboard 上的聚合指标。

最新结果

以下是 2023-10-01T16:31:47.992543 运行的最新结果

python { "all": { "acc": 0.2795859427889157, "acc_stderr": 0.03244654146727709, "acc_norm": 0.283431508310814, "acc_norm_stderr": 0.032446107426975616, "mc1": 0.23255813953488372, "mc1_stderr": 0.014789157531080512, "mc2": 0.38860179255046867, "mc2_stderr": 0.014093255696402213 }, "harness|arc:challenge|25": { "acc": 0.35665529010238906, "acc_stderr": 0.01399805690262019, "acc_norm": 0.3993174061433447, "acc_norm_stderr": 0.014312094557946704 }, "harness|hellaswag|10": { "acc": 0.4971121290579566, "acc_stderr": 0.004989698183207823, "acc_norm": 0.6813383788090022, "acc_norm_stderr": 0.004650052150094427 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816508, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816508 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2023_10_01T16_31_47.992543
      • path: **/details_harness|arc:challenge|25_2023-10-01T16-31-47.992543.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2023-10-01T16-31-47.992543.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_10_01T16_31_47.992543
      • path: **/details_harness|hellaswag|10_2023-10-01T16-31-47.992543.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2023-10-01T16-31-47.992543.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_10_01T16_31_47.992543
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-management|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-security_studies|5_2023-10-01T16-31-47.992543.parquet
        • **/details_harness|hendrycksTest-sociology|5_2023-10
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