{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.27, "acc_stderr": 0.044619604333847415, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847415 }, "hendrycksTest-anatomy": { "acc": 0.22962962962962963, "acc_stderr": 0.03633384414073465, "acc_norm": 0.22962962962962963, "acc_norm_stderr": 0.03633384414073465 }, "hendrycksTest-astronomy": { "acc": 0.23684210526315788, "acc_stderr": 0.03459777606810535, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.03459777606810535 }, "hendrycksTest-business_ethics": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "hendrycksTest-clinical_knowledge": { "acc": 0.35094339622641507, "acc_stderr": 0.02937364625323469, "acc_norm": 0.35094339622641507, "acc_norm_stderr": 0.02937364625323469 }, "hendrycksTest-college_biology": { "acc": 0.2847222222222222, "acc_stderr": 0.03773809990686933, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.03773809990686933 }, "hendrycksTest-college_chemistry": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "hendrycksTest-college_computer_science": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "hendrycksTest-college_mathematics": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "hendrycksTest-college_medicine": { "acc": 0.3063583815028902, "acc_stderr": 0.03514942551267437, "acc_norm": 0.3063583815028902, "acc_norm_stderr": 0.03514942551267437 }, "hendrycksTest-college_physics": { "acc": 0.17647058823529413, "acc_stderr": 0.03793281185307812, "acc_norm": 0.17647058823529413, "acc_norm_stderr": 0.03793281185307812 }, "hendrycksTest-computer_security": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "hendrycksTest-conceptual_physics": { "acc": 0.33617021276595743, "acc_stderr": 0.030881618520676942, "acc_norm": 0.33617021276595743, "acc_norm_stderr": 0.030881618520676942 }, "hendrycksTest-econometrics": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "hendrycksTest-electrical_engineering": { "acc": 0.30344827586206896, "acc_stderr": 0.038312260488503336, "acc_norm": 0.30344827586206896, "acc_norm_stderr": 0.038312260488503336 }, "hendrycksTest-elementary_mathematics": { "acc": 0.24603174603174602, "acc_stderr": 0.022182037202948365, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.022182037202948365 }, "hendrycksTest-formal_logic": { "acc": 0.29365079365079366, "acc_stderr": 0.04073524322147127, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.04073524322147127 }, "hendrycksTest-global_facts": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "hendrycksTest-high_school_biology": { "acc": 0.2806451612903226, "acc_stderr": 0.025560604721022902, "acc_norm": 0.2806451612903226, "acc_norm_stderr": 0.025560604721022902 }, "hendrycksTest-high_school_chemistry": { "acc": 0.270935960591133, "acc_stderr": 0.031270907132976984, "acc_norm": 0.270935960591133, "acc_norm_stderr": 0.031270907132976984 }, "hendrycksTest-high_school_computer_science": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "hendrycksTest-high_school_european_history": { "acc": 0.30303030303030304, "acc_stderr": 0.03588624800091707, "acc_norm": 0.30303030303030304, "acc_norm_stderr": 0.03588624800091707 }, "hendrycksTest-high_school_geography": { "acc": 0.2777777777777778, "acc_stderr": 0.03191178226713549, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.03191178226713549 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.22279792746113988, "acc_stderr": 0.03003114797764155, "acc_norm": 0.22279792746113988, "acc_norm_stderr": 0.03003114797764155 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.24102564102564103, "acc_stderr": 0.021685546665333195, "acc_norm": 0.24102564102564103, "acc_norm_stderr": 0.021685546665333195 }, "hendrycksTest-high_school_mathematics": { "acc": 0.24814814814814815, "acc_stderr": 0.026335739404055803, "acc_norm": 0.24814814814814815, "acc_norm_stderr": 0.026335739404055803 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.31092436974789917, "acc_stderr": 0.03006676158297794, "acc_norm": 0.31092436974789917, "acc_norm_stderr": 0.03006676158297794 }, "hendrycksTest-high_school_physics": { "acc": 0.33774834437086093, "acc_stderr": 0.038615575462551684, "acc_norm": 0.33774834437086093, "acc_norm_stderr": 0.038615575462551684 }, "hendrycksTest-high_school_psychology": { "acc": 0.3155963302752294, "acc_stderr": 0.019926117513869666, "acc_norm": 0.3155963302752294, "acc_norm_stderr": 0.019926117513869666 }, "hendrycksTest-high_school_statistics": { "acc": 0.35648148148148145, "acc_stderr": 0.032664783315272714, "acc_norm": 0.35648148148148145, "acc_norm_stderr": 0.032664783315272714 }, "hendrycksTest-high_school_us_history": { "acc": 0.30392156862745096, "acc_stderr": 0.032282103870378935, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.032282103870378935 }, "hendrycksTest-high_school_world_history": { "acc": 0.31645569620253167, "acc_stderr": 0.030274974880218977, "acc_norm": 0.31645569620253167, "acc_norm_stderr": 0.030274974880218977 }, "hendrycksTest-human_aging": { "acc": 0.24663677130044842, "acc_stderr": 0.028930413120910877, "acc_norm": 0.24663677130044842, "acc_norm_stderr": 0.028930413120910877 }, "hendrycksTest-human_sexuality": { "acc": 0.2595419847328244, "acc_stderr": 0.03844876139785271, "acc_norm": 0.2595419847328244, "acc_norm_stderr": 0.03844876139785271 }, "hendrycksTest-international_law": { "acc": 0.2892561983471074, "acc_stderr": 0.04139112727635465, "acc_norm": 0.2892561983471074, "acc_norm_stderr": 0.04139112727635465 }, "hendrycksTest-jurisprudence": { "acc": 0.26851851851851855, "acc_stderr": 0.04284467968052191, "acc_norm": 0.26851851851851855, "acc_norm_stderr": 0.04284467968052191 }, "hendrycksTest-logical_fallacies": { "acc": 0.2147239263803681, "acc_stderr": 0.03226219377286774, "acc_norm": 0.2147239263803681, "acc_norm_stderr": 0.03226219377286774 }, "hendrycksTest-machine_learning": { "acc": 0.25892857142857145, "acc_stderr": 0.04157751539865629, "acc_norm": 0.25892857142857145, "acc_norm_stderr": 0.04157751539865629 }, "hendrycksTest-management": { "acc": 0.27184466019417475, "acc_stderr": 0.044052680241409216, "acc_norm": 0.27184466019417475, "acc_norm_stderr": 0.044052680241409216 }, "hendrycksTest-marketing": { "acc": 0.3247863247863248, "acc_stderr": 0.03067902276549883, "acc_norm": 0.3247863247863248, "acc_norm_stderr": 0.03067902276549883 }, "hendrycksTest-medical_genetics": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "hendrycksTest-miscellaneous": { "acc": 0.31417624521072796, "acc_stderr": 0.016599291735884907, "acc_norm": 0.31417624521072796, "acc_norm_stderr": 0.016599291735884907 }, "hendrycksTest-moral_disputes": { "acc": 0.2976878612716763, "acc_stderr": 0.02461705538867701, "acc_norm": 0.2976878612716763, "acc_norm_stderr": 0.02461705538867701 }, "hendrycksTest-moral_scenarios": { "acc": 0.2636871508379888, "acc_stderr": 0.01473692638376196, "acc_norm": 0.2636871508379888, "acc_norm_stderr": 0.01473692638376196 }, "hendrycksTest-nutrition": { "acc": 0.30392156862745096, "acc_stderr": 0.026336613469046647, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.026336613469046647 }, "hendrycksTest-philosophy": { "acc": 0.2829581993569132, "acc_stderr": 0.025583062489984824, "acc_norm": 0.2829581993569132, "acc_norm_stderr": 0.025583062489984824 }, "hendrycksTest-prehistory": { "acc": 0.2932098765432099, "acc_stderr": 0.02532988817190092, "acc_norm": 0.2932098765432099, "acc_norm_stderr": 0.02532988817190092 }, "hendrycksTest-professional_accounting": { "acc": 0.24822695035460993, "acc_stderr": 0.025770015644290396, "acc_norm": 0.24822695035460993, "acc_norm_stderr": 0.025770015644290396 }, "hendrycksTest-professional_law": { "acc": 0.2646675358539765, "acc_stderr": 0.011267332992845517, "acc_norm": 0.2646675358539765, "acc_norm_stderr": 0.011267332992845517 }, "hendrycksTest-professional_medicine": { "acc": 0.2426470588235294, "acc_stderr": 0.02604066247420126, "acc_norm": 0.2426470588235294, "acc_norm_stderr": 0.02604066247420126 }, "hendrycksTest-professional_psychology": { "acc": 0.272875816993464, "acc_stderr": 0.01802047414839358, "acc_norm": 0.272875816993464, "acc_norm_stderr": 0.01802047414839358 }, "hendrycksTest-public_relations": { "acc": 0.3090909090909091, "acc_stderr": 0.044262946482000985, "acc_norm": 0.3090909090909091, "acc_norm_stderr": 0.044262946482000985 }, "hendrycksTest-security_studies": { "acc": 0.23673469387755103, "acc_stderr": 0.027212835884073167, "acc_norm": 0.23673469387755103, "acc_norm_stderr": 0.027212835884073167 }, "hendrycksTest-sociology": { "acc": 0.29850746268656714, "acc_stderr": 0.032357437893550424, "acc_norm": 0.29850746268656714, "acc_norm_stderr": 0.032357437893550424 }, "hendrycksTest-us_foreign_policy": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "hendrycksTest-virology": { "acc": 0.3192771084337349, "acc_stderr": 0.03629335329947859, "acc_norm": 0.3192771084337349, "acc_norm_stderr": 0.03629335329947859 }, "hendrycksTest-world_religions": { "acc": 0.3742690058479532, "acc_stderr": 0.037116011853894806, "acc_norm": 0.3742690058479532, "acc_norm_stderr": 0.037116011853894806 } }, "versions": { "hendrycksTest-abstract_algebra": 1, "hendrycksTest-anatomy": 1, "hendrycksTest-astronomy": 1, "hendrycksTest-business_ethics": 1, "hendrycksTest-clinical_knowledge": 1, "hendrycksTest-college_biology": 1, "hendrycksTest-college_chemistry": 1, "hendrycksTest-college_computer_science": 1, "hendrycksTest-college_mathematics": 1, "hendrycksTest-college_medicine": 1, "hendrycksTest-college_physics": 1, "hendrycksTest-computer_security": 1, "hendrycksTest-conceptual_physics": 1, "hendrycksTest-econometrics": 1, "hendrycksTest-electrical_engineering": 1, "hendrycksTest-elementary_mathematics": 1, "hendrycksTest-formal_logic": 1, "hendrycksTest-global_facts": 1, "hendrycksTest-high_school_biology": 1, "hendrycksTest-high_school_chemistry": 1, "hendrycksTest-high_school_computer_science": 1, "hendrycksTest-high_school_european_history": 1, "hendrycksTest-high_school_geography": 1, "hendrycksTest-high_school_government_and_politics": 1, "hendrycksTest-high_school_macroeconomics": 1, "hendrycksTest-high_school_mathematics": 1, "hendrycksTest-high_school_microeconomics": 1, "hendrycksTest-high_school_physics": 1, "hendrycksTest-high_school_psychology": 1, "hendrycksTest-high_school_statistics": 1, "hendrycksTest-high_school_us_history": 1, "hendrycksTest-high_school_world_history": 1, "hendrycksTest-human_aging": 1, "hendrycksTest-human_sexuality": 1, "hendrycksTest-international_law": 1, "hendrycksTest-jurisprudence": 1, "hendrycksTest-logical_fallacies": 1, "hendrycksTest-machine_learning": 1, "hendrycksTest-management": 1, "hendrycksTest-marketing": 1, "hendrycksTest-medical_genetics": 1, "hendrycksTest-miscellaneous": 1, "hendrycksTest-moral_disputes": 1, "hendrycksTest-moral_scenarios": 1, "hendrycksTest-nutrition": 1, "hendrycksTest-philosophy": 1, "hendrycksTest-prehistory": 1, "hendrycksTest-professional_accounting": 1, "hendrycksTest-professional_law": 1, "hendrycksTest-professional_medicine": 1, "hendrycksTest-professional_psychology": 1, "hendrycksTest-public_relations": 1, "hendrycksTest-security_studies": 1, "hendrycksTest-sociology": 1, "hendrycksTest-us_foreign_policy": 1, "hendrycksTest-virology": 1, "hendrycksTest-world_religions": 1 }, "config": { "model": "hf-causal", "model_args": "pretrained=./workdir_7b_16mix/ckpt_357", "num_fewshot": 5, "batch_size": "1", "batch_sizes": [], "device": null, "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }