five

open-llm-leaderboard-old/details_jisukim8873__falcon-7B-case-6

收藏
Hugging Face2024-02-16 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_jisukim8873__falcon-7B-case-6
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jisukim8873/falcon-7B-case-6的评估运行中自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割使用运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了运行的所有聚合结果,并用于计算和显示在Open LLM Leaderboard上的聚合指标。

该数据集是在模型jisukim8873/falcon-7B-case-6的评估运行中自动创建的。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割使用运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了运行的所有聚合结果,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

数据集摘要

该数据集是在对模型 jisukim8873/falcon-7B-case-6 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 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拆分,拆分名称使用运行的时间戳。
  • "train" 拆分始终指向最新的结果。
  • 额外的 "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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_jisukim8873__falcon-7B-case-6", "harness_winogrande_5", split="train")

最新结果

以下是 2024-02-16T07:12:28.485530 运行的最新结果

python { "all": { "acc": 0.2999741752010719, "acc_stderr": 0.032195034392452436, "acc_norm": 0.30103224915319854, "acc_norm_stderr": 0.032944763241990214, "mc1": 0.25091799265605874, "mc1_stderr": 0.015176985027707687, "mc2": 0.364571668218642, "mc2_stderr": 0.014117416041879967 }, "harness|arc:challenge|25": { "acc": 0.4274744027303754, "acc_stderr": 0.014456862944650654, "acc_norm": 0.46501706484641636, "acc_norm_stderr": 0.014575583922019665 }, "harness|hellaswag|10": { "acc": 0.5976897032463653, "acc_stderr": 0.0048936170149753, "acc_norm": 0.7849034056960765, "acc_norm_stderr": 0.004100495978108428 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2962962962962963, "acc_stderr": 0.03944624162501116, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.03944624162501116 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3026315789473684, "acc_stderr": 0.037385206761196686, "acc_norm": 0.3026315789473684, "acc_norm_stderr": 0.037385206761196686 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3018867924528302, "acc_stderr": 0.028254200344438662, "acc_norm": 0.3018867924528302, "acc_norm_stderr": 0.028254200344438662 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2658959537572254, "acc_stderr": 0.03368762932259431, "acc_norm": 0.2658959537572254, "acc_norm_stderr": 0.03368762932259431 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.040925639582376536, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.040925639582376536 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3148936170212766, "acc_stderr": 0.03036358219723817, "acc_norm": 0.3148936170212766, "acc_norm_stderr": 0.03036358219723817 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.27586206896551724, "acc_stderr": 0.037245636197746325, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.02256989707491841, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.02256989707491841 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1349206349206349, "acc_stderr": 0.030557101589417515, "acc_norm": 0.1349206349206349, "acc_norm_stderr": 0.030557101589417515 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.33225806451612905, "acc_stderr": 0.02679556084812279, "acc_norm": 0.33225806451612905, "acc_norm_stderr": 0.02679556084812279 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3497536945812808, "acc_stderr": 0.03355400904969566, "acc_norm": 0.3497536945812808, "acc_norm_stderr": 0.03355400904969566 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3151515151515151, "acc_stderr": 0.0362773057502241, "acc_norm": 0.3151515151515151, "acc_norm_stderr": 0.0362773057502241 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.30303030303030304, "acc_stderr": 0.03274287914026869, "acc_norm": 0.30303030303030304, "acc_norm_stderr": 0.03274287914026869 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.25906735751295334, "acc_stderr": 0.03161877917935411, "acc_norm": 0.25906735751295334, "acc_norm_stderr": 0.03161877917935411 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.24615384615384617, "acc_stderr": 0.021840866990423095, "acc_norm": 0.24615384615384617, "acc_norm_stderr": 0.021840866990423095 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.026202766534652155, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.026202766534652155 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.24369747899159663, "acc_stderr": 0.027886828078380572, "acc_norm": 0.24369747899159663, "acc_norm_stderr": 0.027886828078380572 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.2781456953642384, "acc_stderr": 0.03658603262763743, "acc_norm": 0.2781456953642384, "acc_norm_stderr": 0.03658603262763743 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.28990825688073396, "acc_stderr": 0.019453066609201597, "acc_norm": 0.28990825688073396, "acc_norm_stderr": 0.019453066609201597 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.19444444444444445, "acc_stderr": 0.026991454502036744, "acc_norm": 0.19444444444444445, "acc_norm_stderr": 0.026991454502036744 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.27450980392156865, "acc_stderr": 0.03132179803083289, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.03132179803083289 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.31645569620253167, "acc_stderr": 0.03027497488021897, "acc_norm": 0.31645569620253167, "acc_norm_stderr": 0.03027497488021897 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.37668161434977576, "acc_stderr": 0.03252113489929188, "acc_norm": 0.37668161434977576, "acc_norm_stderr": 0.03252113489929188 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.26717557251908397, "acc_stderr": 0.03880848301082396, "acc_norm": 0.26717557251908397, "acc_norm_stderr": 0.03880848301082396 }, "harness|hendrycksTest-international_law|5": { "acc": 0.4132231404958678, "acc_stderr": 0.04495087843548408, "acc_norm": 0.4132231404958678, "acc_norm_stderr": 0.04495087843548408 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.3148148148148148, "acc_stderr": 0.04489931073591312, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.04489931073591312 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.2883435582822086, "acc_stderr": 0.035590395316173425, "acc_norm": 0.2883435582822086, "acc_norm_stderr": 0.035590395316173425 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.2857142857142857, "acc_stderr": 0.042878587513404565, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.042878587513404565 }, "harness|hendrycksTest-management|5": { "acc": 0.32038834951456313, "acc_stderr": 0.04620284082280039, "acc_norm": 0.32038834951456313, "acc_norm_stderr": 0.04620284082280039 }, "harness|hendrycksTest-marketing|5": { "acc": 0.3076923076923077, "acc_stderr": 0.03023638994217307, "acc_norm": 0.3076923076923077, "acc_norm_stderr": 0.03023638994217307 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.3537675606641124, "acc_stderr": 0.017098184708161903, "acc_norm": 0.3537675606641124, "acc_norm_stderr": 0.017098184708161903 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.3236994219653179, "acc_stderr": 0.025190181327608422, "acc_norm": 0.3236994219653179, "acc_norm_stderr": 0.025190181327608422 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.24692737430167597, "acc_stderr": 0.014422292204808835, "acc_norm": 0.24692737430167597, "acc_norm_stderr": 0.014422292204808835 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.3202614379084967, "acc_stderr": 0.026716118380156844, "acc_norm": 0.3202614379084967, "acc_norm_stderr": 0.026716118380156844 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.3183279742765273, "acc_stderr": 0.026457225067811025, "acc_norm": 0.3183279742765273, "acc_norm_stderr": 0.026457225067811025 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.2777777777777778, "acc_stderr": 0.024922001168886335, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.024922001168886335 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.24113475177304963, "acc_stderr": 0.02551873104953776, "acc_norm": 0.24113475177304963, "acc_norm_stderr": 0.02551873104953776 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.2627118644067797, "acc_stderr": 0.01124054551499567, "acc_norm": 0.2627118644067797, "acc_norm_stderr": 0.01124054551499567 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.21323529411764705, "acc_stderr": 0.024880971512294292, "acc_norm": 0.21323529411764705, "acc_norm_stderr": 0.024880971512294292 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.2630718954248366, "acc_stderr": 0.017812676542320657, "acc_norm": 0.2630718954248366, "acc_norm_stderr": 0.017812676542320657 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.24545454545454545, "acc_stderr": 0.04122066502878284, "acc_norm": 0.24545454545454545, "acc_norm_stderr": 0.04122066502878284 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.24489795918367346, "acc_stderr": 0.02752963744017493, "acc_norm": 0.24489795918367346, "acc_norm_stderr": 0.02752963744017493 }, "harness|hendrycksTest-sociology|5": { "acc": 0.3034825870646766, "acc_stderr": 0.032510068164586174, "acc_norm": 0.3034825870646766, "acc_norm_stderr": 0.032510068164586174 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-virology|5": { "acc": 0.3253012048192771, "acc_stderr": 0.03647168523683227, "acc_norm": 0.3253012048192771, "acc_norm_stderr": 0.03647168523683227 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.3391812865497076, "acc_stderr": 0.03631053496488905, "acc_norm": 0.3391812865497076, "acc_norm_stderr": 0.03631053496488905 }, "harness|truthfulqa:mc|0": { "mc1": 0.25091799265605874, "mc1_stderr": 0.015176985027707687, "mc2": 0.364571668218642, "mc2_stderr": 0.014117416041879967 }, "harness|winogrande|5": { "acc": 0.7008681925808997, "acc_stderr": 0.012868639066091541 }, "harness|gsm8k|5": { "acc": 0.06141015921152388, "acc_stderr": 0.006613027536586305 } }

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