open-llm-leaderboard-old/details_Technoculture__Medorca-4x7b
收藏数据集概述
数据集简介
该数据集是在评估模型Technoculture/Medorca-4x7b在Open LLM Leaderboard上的运行过程中自动创建的。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集从1次运行中创建。每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 训练分割："train"分割始终指向最新的结果。
- 结果配置：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
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Technoculture__Medorca-4x7b", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-16T09:31:13.388605运行的最新结果：
python { "all": { "acc": 0.24277591604603688, "acc_stderr": 0.030362031381414405, "acc_norm": 0.2439454714476596, "acc_norm_stderr": 0.031170707455863384, "mc1": 0.23623011015911874, "mc1_stderr": 0.014869755015871093, "mc2": 0.484210555153098, "mc2_stderr": 0.016831351518748705 }, "harness|arc:challenge|25": { "acc": 0.2295221843003413, "acc_stderr": 0.012288926760890776, "acc_norm": 0.2935153583617747, "acc_norm_stderr": 0.013307250444941117 }, "harness|hellaswag|10": { "acc": 0.25473013343955386, "acc_stderr": 0.0043481894593365355, "acc_norm": 0.25721967735510853, "acc_norm_stderr": 0.004362081806560237 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.24444444444444444, "acc_stderr": 0.03712537833614866, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2679245283018868, "acc_stderr": 0.027257260322494845, "acc_norm": 0.2679245283018868, "acc_norm_stderr": 0.027257260322494845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.040201512610368445, "acc_norm": 0.2, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.21965317919075145, "acc_stderr": 0.031568093627031744, "acc_norm": 0.21965317919075145, "acc_norm_stderr": 0.031568093627031744 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179961, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179961 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.32340425531914896, "acc_stderr": 0.030579442773610334, "acc_norm": 0.32340425531914896, "acc_norm_stderr": 0.030579442773610334 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436716, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436716 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2827586206896552, "acc_stderr": 0.03752833958003337, "acc_norm": 0.2827586206896552, "acc_norm_stderr": 0.03752833958003337 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.18253968253968253, "acc_stderr": 0.03455071019102148, "acc_norm": 0.18253968253968253, "acc_norm_stderr": 0.03455071019102148 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.27419354838709675, "acc_stderr": 0.025378139970885196, "acc_norm": 0.27419354838709675, "acc_norm_stderr": 0.025378139970885196 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.24630541871921183, "acc_stderr": 0.030315099285617732, "acc_norm": 0.24630541871921183, "acc_norm_stderr": 0.030315099285617732 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.24242424242424243, "acc_stderr": 0.03346409881055953, "acc_norm": 0.24242424242424243, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21717171717171718, "acc_stderr": 0.029376616484945637, "acc_norm": 0.21717171717171718, "acc_norm_stderr": 0.029376616484945637 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.02869787397186067, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.02869787397186067 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2230769230769231, "acc_stderr": 0.021107730127243998, "acc_norm": 0.2230769230769231, "acc_norm_stderr": 0.021107730127243998 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.02620276653465215, "acc_norm": 0.244
