open-llm-leaderboard-old/details_allknowingroger__NeuralDolphin-7B-slerp
收藏数据集概述
数据集简介
该数据集是在评估模型allknowingroger/NeuralDolphin-7B-slerp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。
- 数据来源:数据集由1次运行生成,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。
- 最新结果:"train"分割始终指向最新的结果。
- 汇总结果:一个额外的配置"results"存储所有运行的汇总结果,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_allknowingroger__NeuralDolphin-7B-slerp", "harness_winogrande_5", split="train")
最新结果
以下是2024-04-10T19:59:48.653872运行的最新结果:
python { "all": { "acc": 0.6523407261257382, "acc_stderr": 0.0320281547439977, "acc_norm": 0.6528519880112322, "acc_norm_stderr": 0.03268247380255343, "mc1": 0.44430844553243576, "mc1_stderr": 0.01739458625074317, "mc2": 0.608533071036163, "mc2_stderr": 0.015352819851955538 }, "harness|arc:challenge|25": { "acc": 0.64419795221843, "acc_stderr": 0.013990571137918762, "acc_norm": 0.6774744027303754, "acc_norm_stderr": 0.013659980894277366 }, "harness|hellaswag|10": { "acc": 0.6749651463851822, "acc_stderr": 0.004674306182532136, "acc_norm": 0.8568014339772954, "acc_norm_stderr": 0.0034955936625207483 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998904, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.62, "acc_stderr": 0.048783173121456316, "acc_norm": 0.62, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7056603773584905, "acc_stderr": 0.02804918631569525, "acc_norm": 0.7056603773584905, "acc_norm_stderr": 0.02804918631569525 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.04897104952726366, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.04897104952726366 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.574468085106383, "acc_stderr": 0.03232146916224468, "acc_norm": 0.574468085106383, "acc_norm_stderr": 0.03232146916224468 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555497, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555497 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.43915343915343913, "acc_stderr": 0.025559920550531006, "acc_norm": 0.43915343915343913, "acc_norm_stderr": 0.025559920550531006 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7806451612903226, "acc_stderr": 0.023540799358723295, "acc_norm": 0.7806451612903226, "acc_norm_stderr": 0.023540799358723295 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8131313131313131, "acc_stderr": 0.027772533334218967, "acc_norm": 0.8131313131313131, "acc_norm_stderr": 0.027772533334218967 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.023381935348121437, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.023381935348121437 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6820512820512821, "acc_stderr": 0.023610884308927865, "acc_norm": 0.6820512820512821, "acc_norm_stderr": 0.023610884308927865 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.029116617606083018, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.029116617606083018 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6932773109243697, "acc_stderr": 0.029953823891887027, "acc_norm": 0.6932773109243697, "acc_norm_stderr": 0.029953823891887027 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.3443708609271523, "acc_stderr": 0.038796870240733264, "acc_norm": 0.3443708609271523, "acc_norm_stderr": 0.038796870240733264 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8440366972477065, "acc_stderr": 0.01555580271359017, "acc_norm": 0.8440366972477065, "acc_norm_stderr": 0.01555580271359017 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5138888888888888, "acc_stderr": 0.03408655867977749, "acc_norm": 0.5138888888888888, "acc_norm_stderr": 0.03408655867977749 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.8186274509803921, "acc_stderr": 0.027044621719474082, "acc_norm": 0.8186274509803921, "acc_norm_stderr": 0.027044621719474082 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.7932489451476793, "acc_stderr": 0.026361651668389094, "acc_norm": 0.7932489451476793, "acc_norm_stderr": 0.026361651668389094 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.6681614349775785, "acc_stderr": 0.03160295143776679, "acc_norm": 0.6681614349775785, "acc_norm_stderr": 0.03160295143776679 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.7862595419847328, "acc_stderr": 0.0359546161177469, "acc_norm": 0.7862595419847328, "acc_norm_stderr": 0.0359546161177469 }, "harness|hendrycksTest-international_law|5": { "acc": 0.7851239669421488, "acc_stderr": 0.037494924487096966, "acc_norm": 0.7851239669421488, "acc_norm_stderr": 0.037494924487096966 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.8148148148148148, "acc_stderr": 0.03755265865037182, "acc_norm": 0.8148148148148148, "acc_norm_stderr": 0.03755265865037182 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7730061349693251, "acc_stderr": 0.03291099578615769, "acc_norm": 0.7730061349693251, "acc_norm_stderr": 0.03291099578615769 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.4642857142857143, "acc_stderr": 0.04733667890053756, "acc_norm": 0.4642857142857143, "acc_norm_stderr": 0.04733667890053756 }, "harness|hendrycksTest-management|5": { "acc": 0.7864077669902912, "acc_stderr": 0.040580420156460344, "acc_norm": 0.7864077669902912, "acc_norm_stderr": 0.040580420156460344 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8760683760683761, "acc_stderr": 0.02158649400128137, "acc_norm": 0.8760683760683761, "acc_norm_stderr": 0.02158649400128137 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909282, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8314176245210728, "acc_stderr": 0.013387895731543604, "acc_norm": 0.8314176245210728, "acc_norm_stderr": 0.013387895731543604 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.7312138728323699, "acc_stderr": 0.023868003262500104, "acc_norm": 0.7312138728323699, "acc_norm_stderr": 0.023868003262500104 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.4134078212290503, "acc_stderr": 0.016469814928406164, "acc_norm": 0.4134078212290503, "acc_norm_stderr": 0.016469814928406164 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.738562091503268, "acc_stderr": 0.025160998214292456, "acc_norm": 0.738562091503268, "acc_norm_stderr": 0.025160998214292456 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.7009646302250804, "acc_stderr": 0.026003301117885135, "acc_norm": 0.7009646302250804, "acc_norm_stderr": 0.026003301117885135 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.75, "acc_stderr": 0.02409347123262133, "acc_norm": 0.75, "acc_norm_stderr": 0.02409347123262133 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.45390070921985815, "acc_stderr": 0.029700453247291463, "acc_norm": 0.45390070921985815, "acc_norm_stderr": 0.029700453247291463 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.46153846153846156, "acc_stderr": 0.01273239828619044, "acc_norm": 0.46153846153846156, "acc_norm_stderr": 0.01273239828619044 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6727941176470589, "acc_stderr": 0.028501452860396556, "acc_norm": 0.6727941176470589, "acc_norm_stderr": 0.028501452860396556 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.684640522875817, "acc_stderr": 0.01879808628488689, "acc_norm": 0.684640522875817, "acc_norm_stderr": 0.01879808628488689 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6818181818181818, "acc_stderr": 0.04461272175910509, "acc_norm": 0.6818181818181818, "acc_norm_stderr": 0.04461272175910509 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7510204081632653, "acc_stderr": 0.027682979522960238, "acc_norm": 0.7510204081632653, "acc_norm_stderr": 0.027682979522960238 }, "harness|hendrycksTest-sociology|5": { "acc": 0.8407960199004975, "acc_stderr": 0.02587064676616914, "acc_norm": 0.8407960199004975, "acc_norm_stderr": 0.02587064676616914 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.84, "acc_stderr": 0.03684529491774709, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-virology|5": { "acc": 0.5421686746987951, "acc_stderr": 0.0387862677100236, "acc_norm": 0.5421686746987951, "acc_norm_stderr": 0.0387862677100236 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8304093567251462, "acc_stderr": 0.02878210810540171, "acc_norm": 0.8304093567251462, "acc_norm_stderr": 0.02878210810540171 }, "harness|truthfulqa:mc|0": { "mc1": 0.44430844553243576, "mc1_stderr": 0.01739458625074317, "mc2": 0.608533071036163, "mc2_stderr": 0.015352819851955538 }, "harness|winogrande|5": { "acc": 0.8042620363062352, "acc_stderr": 0.011151145042218327 }, "harness|gsm8k|5": { "acc": 0.6853677028051555, "acc_stderr": 0.012791037227336034 } }



