open-llm-leaderboard-old/details_nlpguy__Hermes-low-tune-3.1

该数据集是在评估模型nlpguy/Hermes-low-tune-3.1时自动生成的，包含63个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果存储在不同的分割中，分割名称使用运行的时间戳命名。train分割始终指向最新的结果。此外，数据集还包含一个名为results的配置，用于存储所有运行的聚合结果，并用于计算和展示在Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

该数据集是在对模型 nlpguy/Hermes-low-tune-3.1 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 数据集包含 63 个配置，每个配置对应一个评估任务。
• 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。
• 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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_nlpguy__Hermes-low-tune-3.1", "harness_winogrande_5", split="train")

最新结果

以下是 2024-01-18T19:43:57.257898 运行的最新结果：

python { "all": { "acc": 0.643479250503199, "acc_stderr": 0.0322077411976957, "acc_norm": 0.6450125760938904, "acc_norm_stderr": 0.032855183947534713, "mc1": 0.3671970624235006, "mc1_stderr": 0.01687480500145318, "mc2": 0.5358664438298202, "mc2_stderr": 0.015241994807091694 }, "harness|arc:challenge|25": { "acc": 0.6194539249146758, "acc_stderr": 0.014188277712349812, "acc_norm": 0.6544368600682594, "acc_norm_stderr": 0.013896938461145678 }, "harness|hellaswag|10": { "acc": 0.6568412666799442, "acc_stderr": 0.004737936758047634, "acc_norm": 0.8460466042620992, "acc_norm_stderr": 0.003601664838718933 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "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": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.02863723563980089, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.02863723563980089 }, "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": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "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": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6127167630057804, "acc_stderr": 0.03714325906302065, "acc_norm": 0.6127167630057804, "acc_norm_stderr": 0.03714325906302065 }, "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": 0.77, "acc_stderr": 0.042295258468165065, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108101, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108101 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5087719298245614, "acc_stderr": 0.04702880432049615, "acc_norm": 0.5087719298245614, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42592592592592593, "acc_stderr": 0.02546714904546955, "acc_norm": 0.42592592592592593, "acc_norm_stderr": 0.02546714904546955 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7903225806451613, "acc_stderr": 0.023157879349083525, "acc_norm": 0.7903225806451613, "acc_norm_stderr": 0.023157879349083525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5320197044334976, "acc_stderr": 0.03510766597959215, "acc_norm": 0.5320197044334976, "acc_norm_stderr": 0.03510766597959215 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.032250781083062896, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.032250781083062896 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7929292929292929, "acc_stderr": 0.02886977846026704, "acc_norm": 0.7929292929292929, "acc_norm_stderr": 0.02886977846026704 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.02098685459328973, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.02098685459328973 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6230769230769231, "acc_stderr": 0.024570975364225995, "acc_norm": 0.6230769230769231, "acc_norm_stderr": 0.024570975364225995 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32592592592592595, "acc_stderr": 0.028578348365473075, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.028578348365473075 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.680672268907563, "acc_stderr": 0.030283995525884396, "acc_norm": 0.680672268907563, "acc_norm_stderr": 0.030283995525884396 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.33112582781456956, "acc_stderr": 0.038425817186598696, "acc_norm": 0.33112582781456956, "acc_norm_stderr": 0.038425817186598696 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8330275229357799, "acc_stderr": 0.01599015488507338, "acc_norm": 0.8330275229357799, "acc_norm_stderr": 0.01599015488507338 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5092592592592593, "acc_stderr": 0.034093869469927006, "acc_norm": 0.5092592592592593, "acc_norm_stderr": 0.034093869469927006 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.7990196078431373, "acc_stderr": 0.02812597226565437, "acc_norm": 0.7990196078431373, "acc_norm_stderr": 0.02812597226565437 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.8227848101265823, "acc_stderr": 0.024856364184503224, "acc_norm": 0.8227848101265823, "acc_norm_stderr": 0.024856364184503224 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.7130044843049327, "acc_stderr": 0.03036037971029196, "acc_norm": 0.7130044843049327, "acc_norm_stderr": 0.03036037971029196 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.7786259541984732, "acc_stderr": 0.03641297081313728, "acc_norm": 0.7786259541984732, "acc_norm_stderr": 0.03641297081313728 }, "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": 0.7777777777777778, "acc_stderr": 0.0401910747255735, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.0401910747255735 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7914110429447853, "acc_stderr": 0.031921934489347235, "acc_norm": 0.7914110429447853, "acc_norm_stderr": 0.031921934489347235 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.5089285714285714, "acc_stderr": 0.04745033255489123, "acc_norm": 0.5089285714285714, "acc_norm_stderr": 0.04745033255489123 }, "harness|hendrycksTest-management|5": { "acc": 0.7669902912621359, "acc_stderr": 0.04185832598928315, "acc_norm": 0.7669902912621359, "acc_norm_stderr": 0.04185832598928315 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8589743589743589, "acc_stderr": 0.02280138253459753, "acc_norm": 0.8589743589743589, "acc_norm_stderr": 0.02280138253459753 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8237547892720306, "acc_stderr": 0.013625556907993459, "acc_norm": 0.8237547892720306, "acc_norm_stderr": 0.013625556907993459 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.7312138728323699, "acc_stderr": 0.02386800326250011, "acc_norm": 0.7312138728323699, "acc_norm_stderr": 0.02386800326250011 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.3206703910614525, "acc_stderr": 0.015609929559348397, "acc_norm": 0.3206703910614525, "acc_norm_stderr": 0.015609929559348397 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.7516339869281046, "acc_stderr": 0.02473998135511359, "acc_norm": 0.7516339869281046, "acc_norm_stderr": 0.02473998135511359 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.6977491961414791, "acc_stderr": 0.02608270069539966, "acc_norm": 0.6977491961414791, "acc_norm_stderr": 0.02608270069539966 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.7407407407407407, "acc_stderr": 0.024383665531035457, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.024383665531035457 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.4929078014184397, "acc_stderr": 0.02982449855912901, "acc_norm": 0.4929078014184397, "acc_norm_stderr": 0.02982449855912901 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.470013037809648, "acc_stderr": 0.012747248967079069, "acc_norm": 0.470013037809648, "acc_norm_stderr": 0.012747248967079069 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6911764705882353, "acc_stderr": 0.02806499816704009, "acc_norm": 0.6911764705882353, "acc_norm_stderr": 0.02806499816704009 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.673202614379085, "acc_stderr": 0.018975427920507215, "acc_norm": 0.673202614379085, "acc_norm_stderr": 0.018975427920507215 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6545454545454545, "acc_stderr": 0.04554619617541054, "acc_norm": 0.6545454545454545, "acc_norm_stderr": 0.04554619617541054 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7387755102040816, "acc_stderr": 0.028123429335142773, "acc_norm": 0.7387755102040816, "acc_norm_stderr": 0.028123429335142773 }, "harness|hendrycksTest-sociology|5": { "acc": 0.8258706467661692, "acc_stderr": 0.026814951200421603, "acc_norm": 0.8258706467661692, "acc_norm_stderr": 0.026814951200421603 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.87, "acc_stderr": 0.033799766898963086, "acc_norm": 0.87, "acc_norm_stderr": 0.033799766898963086 }, "harness|hendrycksTest-virology|5": { "acc": 0.5481927710843374, "acc_stderr": 0.03874371556587953, "acc_norm": 0.5481927710843374, "acc_norm_stderr": 0.03874371556587953 }, "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": 0.3671970624235006, "mc1_stderr": 0.01687480500145318, "mc2": 0.5358664438298202, "mc2_stderr": 0.015241994807091694 }, "harness|winogrande|5": { "acc": 0.7861089187056038, "acc_stderr": 0.011524466954090255 }, "harness|gsm8k|5": { "acc": 0.6345716451857468, "acc_stderr": 0.013264282030266635 } }