open-llm-leaderboard-old/details_namanpundir__theus_concepttagger
收藏数据集概述
数据集简介
该数据集是在评估模型namanpundir/theus_concepttagger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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_namanpundir__theus_concepttagger", "harness_winogrande_5", split="train")
最新结果
以下是最新结果,来自2024-01-19T09:19:07.563026的运行:
python { "all": { "acc": 0.23155074551271232, "acc_stderr": 0.029928741303991906, "acc_norm": 0.2318198554858782, "acc_norm_stderr": 0.030717432810767893, "mc1": 0.24357405140758873, "mc1_stderr": 0.01502635482491078, "mc2": 0.4824892409622544, "mc2_stderr": 0.01656017052953912 }, "harness|arc:challenge|25": { "acc": 0.20733788395904437, "acc_stderr": 0.011846905782971356, "acc_norm": 0.24573378839590443, "acc_norm_stderr": 0.012581033453730111 }, "harness|hellaswag|10": { "acc": 0.25761800438159727, "acc_stderr": 0.004364287353415452, "acc_norm": 0.2550288787094204, "acc_norm_stderr": 0.004349866376068979 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.18518518518518517, "acc_stderr": 0.03355677216313142, "acc_norm": 0.18518518518518517, "acc_norm_stderr": 0.03355677216313142 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21509433962264152, "acc_stderr": 0.02528839450289137, "acc_norm": 0.21509433962264152, "acc_norm_stderr": 0.02528839450289137 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749874, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749874 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.20899470899470898, "acc_stderr": 0.02094048156533486, "acc_norm": 0.20899470899470898, "acc_norm_stderr": 0.02094048156533486 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.04040610178208841, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.04040610178208841 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.1774193548387097, "acc_stderr": 0.02173254068932927, "acc_norm": 0.1774193548387097, "acc_norm_stderr": 0.02173254068932927 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.15270935960591134, "acc_stderr": 0.02530890453938063, "acc_norm": 0.15270935960591134, "acc_norm_stderr": 0.02530890453938063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.17676767676767677, "acc_stderr": 0.027178752639044915, "acc_norm": 0.17676767676767677, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.028697873971860664, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.028697873971860664 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.20256410256410257, "acc_stderr": 0.020377660970371372, "acc_norm": 0.20256410256410257, "acc_norm_stderr": 0.020377660970371372 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2111111111111111, "acc_stderr": 0.024882116857655075, "acc_norm": 0.2111111111111111, "acc_norm_stderr": 0.024882116857655075 }, "harness|hendrycksTest-high_school_microeconomics|5": { "



