open-llm-leaderboard-old/details_VAGOsolutions__SauerkrautLM-Qwen-32b
收藏数据集概述
数据集摘要
该数据集是在评估模型 VAGOsolutions/SauerkrautLM-Qwen-32b 在 Open LLM Leaderboard 上的自动创建的。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。
加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_VAGOsolutions__SauerkrautLM-Qwen-32b", "harness_winogrande_5", split="train")
最新结果
这些是最新结果的示例: python { "all": { "acc": 0.7340517879431272, "acc_stderr": 0.029409627571625768, "acc_norm": 0.7406545731638753, "acc_norm_stderr": 0.029970385595780122, "mc1": 0.4320685434516524, "mc1_stderr": 0.017341202394988257, "mc2": 0.6103953872847286, "mc2_stderr": 0.01530815239070466 }, "harness|arc:challenge|25": { "acc": 0.5784982935153583, "acc_stderr": 0.014430197069326021, "acc_norm": 0.5878839590443686, "acc_norm_stderr": 0.014383915302225403 }, "harness|hellaswag|10": { "acc": 0.6279625572595101, "acc_stderr": 0.004823604775015907, "acc_norm": 0.8215494921330412, "acc_norm_stderr": 0.003821090082721713 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6370370370370371, "acc_stderr": 0.04153948404742398, "acc_norm": 0.6370370370370371, "acc_norm_stderr": 0.04153948404742398 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8486842105263158, "acc_stderr": 0.029162631596843982, "acc_norm": 0.8486842105263158, "acc_norm_stderr": 0.029162631596843982 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7811320754716982, "acc_stderr": 0.025447863825108632, "acc_norm": 0.7811320754716982, "acc_norm_stderr": 0.025447863825108632 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8402777777777778, "acc_stderr": 0.03063557897209328, "acc_norm": 0.8402777777777778, "acc_norm_stderr": 0.03063557897209328 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7745664739884393, "acc_stderr": 0.03186209851641144, "acc_norm": 0.7745664739884393, "acc_norm_stderr": 0.03186209851641144 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.49019607843137253, "acc_stderr": 0.04974229460422817, "acc_norm": 0.49019607843137253, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7574468085106383, "acc_stderr": 0.028020226271200217, "acc_norm": 0.7574468085106383, "acc_norm_stderr": 0.028020226271200217 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5263157894736842, "acc_stderr": 0.046970851366478626, "acc_norm": 0.5263157894736842, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6896551724137931, "acc_stderr": 0.03855289616378948, "acc_norm": 0.6896551724137931, "acc_norm_stderr": 0.03855289616378948 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6693121693121693, "acc_stderr": 0.024229965298425086, "acc_norm": 0.6693121693121693, "acc_norm_stderr": 0.024229965298425086 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8709677419354839, "acc_stderr": 0.019070889254792753, "acc_norm": 0.8709677419354839, "acc_norm_stderr": 0.019070889254792753 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6354679802955665, "acc_stderr": 0.0338640574606209, "acc_norm": 0.6354679802955665, "acc_norm_stderr": 0.0338640574606209 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.84, "acc_stderr": 0.03684529491774708, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774708 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8666666666666667, "acc_stderr": 0.026544435312706467, "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.026544435312706467 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8939393939393939, "acc_stderr": 0.021938047738853113, "acc_norm": 0.8939393939393939, "acc_norm_stderr": 0.021938047738853113 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9637305699481865, "acc_stderr": 0.013492659751295131, "acc_norm": 0.9637305699481865, "acc_norm_stderr": 0.013492659751295131 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7717948717948718, "acc_stderr": 0.02127839386358628, "acc_norm": 0.7717948717948718, "acc_norm_stderr": 0.02127839386358628 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4925925925925926, "acc_stderr": 0.030482192395191506, "acc_norm": 0.4925925925925926, "acc_norm_stderr": 0.030482192395191506 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8235294117647058, "acc_stderr": 0.02476290267805793, "acc_norm": 0.8235294117647058, "acc_norm_stderr": 0.02476290267805793 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.5298013245033113, "acc_stderr": 0.040752249922169775, "acc_norm": 0.5298013245033113, "acc_norm_stderr": 0.040752249922169775 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.9119266055045872, "acc_stderr": 0.012150743719481653, "acc_norm": 0.9119266055045872, "acc_norm_stderr": 0.012150743719481653 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.032149521478027486, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.032149521478027486 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.9019607843137255, "acc_stderr": 0.020871118455552104, "acc_norm": 0.9019607843137255, "acc_norm_stderr": 0.020871118455552104 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.8860759493670886, "acc_stderr": 0.020681745135884555, "acc_norm": 0.8860759493670886, "acc_norm_stderr": 0.020681745135884555 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.7892376681614349, "acc_stderr": 0.02737309550054019, "acc_norm": 0.7892376681614349, "acc_norm_stderr": 0.02737309550054019 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.8320610687022901, "acc_stderr": 0.032785485373431386, "acc_norm": 0.8320610687022901, "acc_norm_stderr": 0.032785485373431386 }, "harness|hendrycksTest-international_law|5": { "acc": 0.8760330578512396, "acc_stderr": 0.030083098716035202, "acc_norm": 0.8760330578512396, "acc_norm_stderr": 0.030083098716035202 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.8240740740740741, "acc_stderr": 0.036809181416738807, "acc_norm": 0.8240740740740741, "acc_norm_stderr": 0.036809181416738807 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.8220858895705522, "acc_stderr": 0.030047357655806625, "acc_norm": 0.8220858895705522, "acc_norm_stderr": 0.030047357655806625 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.5982142857142857, "acc_stderr": 0.04653333146973647, "acc_norm": 0.5982142857142857, "acc_norm_stderr": 0.04653333146973647 }, "harness|hendrycksTest-management|5": { "acc": 0.8543689320388349, "acc_stderr": 0.0349260647662379, "acc_norm": 0.8543689320388349, "acc_norm_stderr": 0.0349260647662379 }, "harness|hendrycksTest-marketing|5": { "acc": 0.9529914529914529, "acc_stderr": 0.013866120058594843, "acc_norm": 0.9529914529914529, "acc_norm_stderr": 0.013866120058594843 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.81, "acc_stderr": 0.03942772444036623, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8952745849297573, "acc_stderr": 0.010949664098633353, "acc_norm": 0.8952745849297573, "acc_norm_stderr": 0.010949664098633353 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.8034682080924855, "acc_stderr": 0.021393961404363844, "acc_norm": 0.8034682080924855, "acc_norm_stderr": 0.021393961404363844 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.6692737430167598, "acc_stderr": 0.01573502625896612, "acc_norm": 0.6692737430167598, "acc_norm_stderr": 0.01573502625896612 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.7908496732026143, "acc_stderr": 0.02328768531233481, "acc_norm": 0.7908496732026143, "acc_norm_stderr": 0.02328768531233481 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.8135048231511254, "acc_stderr": 0.02212243977248079, "acc_norm": 0.8135048231511254, "acc_norm_stderr": 0.02212243977248079 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.8117283950617284, "acc_stderr": 0.021751866060815875, "acc_norm": 0.8117283950617284, "acc_norm_stderr": 0.021751866060815875 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.5638297872340425, "acc_stderr": 0.02958345203628407, "acc_norm": 0.5638297872340425, "acc_norm_stderr": 0.02958345203628407 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.5782268578878749, "acc_stderr": 0.012612974369390984, "acc_norm": 0.5782268578878749, "acc_norm_stderr": 0.012612974369390984 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.7941176470588235, "acc_stderr": 0.02456220431414231, "acc_norm": 0.7941176470588235, "acc_norm_stderr": 0.02456220431414231 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.7728758169934641, "acc_stderr": 0.016949853279212383, "acc_norm": 0.7728758169934641, "acc_norm_stderr": 0.016949853279212383 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.7090909090909091, "acc_stderr": 0.04350271442923243, "acc_norm": 0.7090909090909091, "acc_norm_stderr": 0.04350271442923243 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7877551020408163, "acc_stderr": 0.026176967197866764, "acc_norm": 0.7877551020408163, "acc_norm_stderr": 0.026176967197866764 }, "harness|hendrycksTest-sociology|5": { "acc": 0.8706467661691543, "acc_stderr": 0.023729830881018533, "acc_norm": 0.8706467661691543, "acc_norm_stderr": 0.023729830881018533 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.93, "acc_stderr": 0.0256432399976243, "acc_norm": 0.93, "acc_norm_stderr": 0.0256432399976243 }, "harness|hendrycksTest-virology|5": { "acc": 0.5783132530120482, "acc_stderr": 0.038444531817709175, "acc_norm": 0.5783132530120482, "acc_norm_stderr": 0.038444531817709175 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8538011695906432, "acc_stderr": 0.02709729011807079, "acc_norm": 0.8538011695906432, "acc_norm_stderr": 0.02709729011807079 }, "harness|truthfulqa:mc|0": { "mc1": 0.4320685434516524, "mc1_stderr": 0.017341202394988257, "mc2": 0.6103953872847286, "mc2_stderr": 0.01530815239070466 }, "harness|winogrande|5": { "acc": 0.813733228097869, "acc_stderr": 0.010941877955676213 }, "harness|gsm8k|5": { "acc": 0.467778620166793, "acc_stderr": 0.013743857303073797 } }



