open-llm-leaderboard-old/details_pansophic__m3
收藏数据集概述
数据集简介
该数据集是在评估模型 pansophic/m3 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，每个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
一个额外的配置 "results" 存储了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_pansophic__m3", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-21T14:25:01.099763 运行的最新结果：
python { "all": { "acc": 0.5671644569574777, "acc_stderr": 0.033995922530025674, "acc_norm": 0.5688418224852516, "acc_norm_stderr": 0.03470075211665992, "mc1": 0.31334149326805383, "mc1_stderr": 0.016238065069059608, "mc2": 0.4498365244105992, "mc2_stderr": 0.015033111764624815 }, "harness|arc:challenge|25": { "acc": 0.5733788395904437, "acc_stderr": 0.014453185592920293, "acc_norm": 0.6040955631399317, "acc_norm_stderr": 0.01429122839353659 }, "harness|hellaswag|10": { "acc": 0.5608444532961562, "acc_stderr": 0.004952698802275647, "acc_norm": 0.7448715395339573, "acc_norm_stderr": 0.004350424750646201 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.045126085985421296, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421296 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45925925925925926, "acc_stderr": 0.04304979692464242, "acc_norm": 0.45925925925925926, "acc_norm_stderr": 0.04304979692464242 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5592105263157895, "acc_stderr": 0.04040311062490436, "acc_norm": 0.5592105263157895, "acc_norm_stderr": 0.04040311062490436 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5849056603773585, "acc_stderr": 0.03032594578928611, "acc_norm": 0.5849056603773585, "acc_norm_stderr": 0.03032594578928611 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6319444444444444, "acc_stderr": 0.04032999053960718, "acc_norm": 0.6319444444444444, "acc_norm_stderr": 0.04032999053960718 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.04943110704237101, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237101 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5664739884393064, "acc_stderr": 0.037786210790920566, "acc_norm": 0.5664739884393064, "acc_norm_stderr": 0.037786210790920566 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.04724007352383888, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.04724007352383888 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.48936170212765956, "acc_stderr": 0.03267862331014063, "acc_norm": 0.48936170212765956, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.41228070175438597, "acc_stderr": 0.04630653203366595, "acc_norm": 0.41228070175438597, "acc_norm_stderr": 0.04630653203366595 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41534391534391535, "acc_stderr": 0.025379524910778408, "acc_norm": 0.41534391534391535, "acc_norm_stderr": 0.025379524910778408 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3412698412698413, "acc_stderr": 0.042407993275749255, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.042407993275749255 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6612903225806451, "acc_stderr": 0.026923446059302844, "acc_norm": 0.6612903225806451, "acc_norm_stderr": 0.026923446059302844 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4482758620689655, "acc_stderr": 0.03499113137676744, "acc_norm": 0.4482758620689655, "acc_norm_stderr": 0.03499113137676744 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6363636363636364, "acc_stderr": 0.037563357751878974, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.037563357751878974 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7222222222222222, "acc_stderr": 0.03191178226713547, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.03191178226713547 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7772020725388601, "acc_stderr": 0.03003114797764154, "acc_norm": 0.7772020725388601, "acc_norm_stderr": 0.03003114797764154 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.541025641025641, "acc_stderr": 0.025265525491284295, "acc_norm": 0.541025641025641, "acc_norm_stderr": 0.025265525491284295 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948496, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.02874204090394
