five

open-llm-leaderboard-old/details_occultml__Helios-10.7B

收藏
Hugging Face2024-01-04 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_occultml__Helios-10.7B
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occultml/Helios-10.7B时自动创建的,用于在Open LLM Leaderboard上进行评估。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命名。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,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occultml/Helios-10.7B时自动创建的,用于在Open LLM Leaderboard上进行评估。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命名。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,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

数据集是在对模型occultml/Helios-10.7B进行评估运行期间自动创建的,评估结果展示在Open LLM Leaderboard上。

数据集组成

  • 数据集包含63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。
  • 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

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_occultml__Helios-10.7B", "harness_winogrande_5", split="train")

最新结果

以下是2024-01-04T12:17:31.612101运行的最新结果: python { "all": { "acc": 0.40988707960386334, "acc_stderr": 0.03401984092738561, "acc_norm": 0.414422676033673, "acc_norm_stderr": 0.03496456895834615, "mc1": 0.30599755201958384, "mc1_stderr": 0.016132229728155045, "mc2": 0.5552021116757884, "mc2_stderr": 0.01659507343053494 }, "harness|arc:challenge|25": { "acc": 0.35665529010238906, "acc_stderr": 0.013998056902620203, "acc_norm": 0.3890784982935154, "acc_norm_stderr": 0.014247309976045609 }, "harness|hellaswag|10": { "acc": 0.3434574785899223, "acc_stderr": 0.004738920624724474, "acc_norm": 0.4660426209918343, "acc_norm_stderr": 0.004978260641742204 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4740740740740741, "acc_stderr": 0.04313531696750575, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.040601270352363966, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.43018867924528303, "acc_stderr": 0.030471445867183238, "acc_norm": 0.43018867924528303, "acc_norm_stderr": 0.030471445867183238 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04076663253918567, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04076663253918567 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816508, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816508 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3872832369942196, "acc_stderr": 0.037143259063020656, "acc_norm": 0.3872832369942196, "acc_norm_stderr": 0.037143259063020656 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.044405219061793275, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.044405219061793275 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.34893617021276596, "acc_stderr": 0.031158522131357797, "acc_norm": 0.34893617021276596, "acc_norm_stderr": 0.031158522131357797 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3508771929824561, "acc_stderr": 0.044895393502706986, "acc_norm": 0.3508771929824561, "acc_norm_stderr": 0.044895393502706986 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.30344827586206896, "acc_stderr": 0.038312260488503336, "acc_norm": 0.30344827586206896, "acc_norm_stderr": 0.038312260488503336 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24338624338624337, "acc_stderr": 0.022101128787415415, "acc_norm": 0.24338624338624337, "acc_norm_stderr": 0.022101128787415415 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523812, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523812 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4935483870967742, "acc_stderr": 0.02844163823354051, "acc_norm": 0.4935483870967742, "acc_norm_stderr": 0.02844163823354051 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3793103448275862, "acc_stderr": 0.034139638059062345, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.034139638059062345 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4666666666666667, "acc_stderr": 0.03895658065271847, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.03895658065271847 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.47474747474747475, "acc_stderr": 0.03557806245087314, "acc_norm": 0.47474747474747475, "acc_norm_stderr": 0.03557806245087314 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5077720207253886, "acc_stderr": 0.036080032255696545, "acc_norm": 0.5077720207253886, "acc_norm_stderr": 0.036080032255696545 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.37435897435897436, "acc_stderr": 0.024537591572830506, "acc_norm": 0.37435897435897436, "acc_norm_stderr": 0.024537591572830506 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027738969632176088, "acc_norm": 0.29259259259259257, "acc_norm_stderr": 0.027738969632176088 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.40756302521008403, "acc_stderr": 0.03191863374478465, "acc_norm": 0.40756302521008403, "acc_norm_stderr": 0.03191863374478465 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.2582781456953642, "acc_stderr": 0.035737053147634576, "acc_norm": 0.2582781456953642, "acc_norm_stderr": 0.035737053147634576 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.4954128440366973, "acc_stderr": 0.021436420955529424, "acc_norm": 0.4954128440366973, "acc_norm_stderr": 0.021436420955529424 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.24537037037037038, "acc_stderr": 0.029346665094372937, "acc_norm": 0.24537037037037038, "acc_norm_stderr": 0.029346665094372937 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.4019607843137255, "acc_stderr": 0.034411900234824655, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.034411900234824655 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.48523206751054854, "acc_stderr": 0.032533028078777386, "acc_norm": 0.48523206751054854, "acc_norm_stderr": 0.032533028078777386 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.4663677130044843, "acc_stderr": 0.033481800170603065, "acc_norm": 0.4663677130044843, "acc_norm_stderr": 0.033481800170603065 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.4580152671755725, "acc_stderr": 0.04369802690578756, "acc_norm": 0.4580152671755725, "acc_norm_stderr": 0.04369802690578756 }, "harness|hendrycksTest-international_law|5": { "acc": 0.6033057851239669, "acc_stderr": 0.044658697805310094, "acc_norm": 0.6033057851239669, "acc_norm_stderr": 0.044658697805310094 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.5370370370370371, "acc_stderr": 0.04820403072760627, "acc_norm": 0.5370370370370371, "acc_norm_stderr": 0.04820403072760627 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.49693251533742333, "acc_stderr": 0.03928297078179663, "acc_norm": 0.49693251533742333, "acc_norm_stderr": 0.03928297078179663 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.30357142857142855, "acc_stderr": 0.04364226155841044, "acc_norm": 0.30357142857142855, "acc_norm_stderr": 0.04364226155841044 }, "harness|hendrycksTest-management|5": { "acc": 0.5048543689320388, "acc_stderr": 0.04950504382128919, "acc_norm": 0.5048543689320388, "acc_norm_stderr": 0.04950504382128919 }, "harness|hendrycksTest-marketing|5": { "acc": 0.5384615384615384, "acc_stderr": 0.03265903381186193, "acc_norm": 0.5384615384615384, "acc_norm_stderr": 0.03265903381186193 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.5504469987228607, "acc_stderr": 0.017788725283507337, "acc_norm": 0.5504469987228607, "acc_norm_stderr": 0.017788725283507337 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.5289017341040463, "acc_stderr": 0.026874085883518348, "acc_norm": 0.5289017341040463, "acc_norm_stderr": 0.026874085883518348 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.2, "acc_stderr": 0.013378001241813068, "acc_norm": 0.2, "acc_norm_stderr": 0.013378001241813068 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.49673202614379086, "acc_stderr": 0.02862930519400354, "acc_norm": 0.49673202614379086, "acc_norm_stderr": 0.02862930519400354 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.5819935691318328, "acc_stderr": 0.028013651891995072, "acc_norm": 0.5819935691318328, "acc_norm_stderr": 0.028013651891995072 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.49382716049382713, "acc_stderr": 0.027818623962583302, "acc_norm": 0.49382716049382713, "acc_norm_stderr": 0.027818623962583302 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.2907801418439716, "acc_stderr": 0.027090664368353178, "acc_norm": 0.2907801418439716, "acc_norm_stderr": 0.027090664368353178 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.29335071707953064, "acc_stderr": 0.011628520449582071, "acc_norm": 0.29335071707953064, "acc_norm_stderr": 0.011628520449582071 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.26838235294117646, "acc_stderr": 0.026917481224377232, "acc_norm": 0.26838235294117646, "acc_norm_stderr": 0.026917481224377232 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.46895424836601307, "acc_stderr": 0.020188804456361883, "acc_norm": 0.46895424836601307, "acc_norm_stderr": 0.020188804456361883 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.4818181818181818, "acc_stderr": 0.04785964010794917, "acc_norm": 0.4818181818181818, "acc_norm_stderr": 0.04785964010794917 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.37142857142857144, "acc_stderr": 0.030932858792789848, "acc_norm": 0.37142857142857144, "acc_norm_stderr": 0.030932858792789848 }, "harness|hendrycksTest-sociology|5": { "acc": 0.5472636815920398, "acc_stderr": 0.03519702717576915, "acc_norm": 0.5472636815920398, "acc_norm_stderr": 0.03519702717576915 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.67, "acc_stderr": 0.047258156262526094, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526094 }, "harness|hendrycksTest-virology|5": { "acc": 0.3614457831325301, "acc_stderr": 0.037400593820293204, "acc_norm": 0.3614457831325301, "acc_norm_stderr": 0.037400593820293204 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.6023391812865497, "acc_stderr": 0.03753638955761691, "acc_norm": 0.6023391812865497, "acc_norm_stderr": 0.03753638955761691 }, "harness|truthfulqa:mc|0": { "mc1": 0.30599755201958384, "mc1_stderr": 0.016132229728155045, "mc2": 0.5552021116757884, "mc2_stderr": 0.01659507343053494 }, "harness|winogrande|5": { "acc": 0.7071823204419889, "acc_stderr": 0.012789321118542616 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2024_01_04T12_17_31.612101
      • path: **/details_harness|arc:challenge|25_2024-01-04T12-17-31.612101.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-01-04T12-17-31.612101.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_01_04T12_17_31.612101
      • path: **/details_harness|gsm8k|5_2024-01-04T12-17-31.612101.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-01-04T12-17-31.612101.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_01_04T12_17_31.612101
      • path: **/details_harness|hellaswag|10_2024-01-04T12-17-31.612101.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-01-04T12-17-31.612101.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_01_04T12_17_31.612101
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-international_law|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-management|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-marketing|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-security_studies|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-sociology|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-virology|5_2024-01-04T12-17-31.612101.parquet
        • **/details_harness|hendrycksTest-world_religions|5_2024-01-04T12-17-31.612101.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