{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "hendrycksTest-anatomy": { "acc": 0.26666666666666666, "acc_stderr": 0.038201699145179055, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.038201699145179055 }, "hendrycksTest-astronomy": { "acc": 0.27631578947368424, "acc_stderr": 0.03639057569952924, "acc_norm": 0.27631578947368424, "acc_norm_stderr": 0.03639057569952924 }, "hendrycksTest-business_ethics": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "hendrycksTest-clinical_knowledge": { "acc": 0.26037735849056604, "acc_stderr": 0.027008766090708104, "acc_norm": 0.26037735849056604, "acc_norm_stderr": 0.027008766090708104 }, "hendrycksTest-college_biology": { "acc": 0.2986111111111111, "acc_stderr": 0.03827052357950756, "acc_norm": 0.2986111111111111, "acc_norm_stderr": 0.03827052357950756 }, "hendrycksTest-college_chemistry": { "acc": 0.22, "acc_stderr": 0.0416333199893227, "acc_norm": 0.22, "acc_norm_stderr": 0.0416333199893227 }, "hendrycksTest-college_computer_science": { "acc": 0.38, "acc_stderr": 0.04878317312145631, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145631 }, "hendrycksTest-college_mathematics": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "hendrycksTest-college_medicine": { "acc": 0.2774566473988439, "acc_stderr": 0.03414014007044036, "acc_norm": 0.2774566473988439, "acc_norm_stderr": 0.03414014007044036 }, "hendrycksTest-college_physics": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179963, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179963 }, "hendrycksTest-computer_security": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "hendrycksTest-conceptual_physics": { "acc": 0.23829787234042554, "acc_stderr": 0.027851252973889778, "acc_norm": 0.23829787234042554, "acc_norm_stderr": 0.027851252973889778 }, "hendrycksTest-econometrics": { "acc": 0.2807017543859649, "acc_stderr": 0.042270544512322, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.042270544512322 }, "hendrycksTest-electrical_engineering": { "acc": 0.3103448275862069, "acc_stderr": 0.03855289616378948, "acc_norm": 0.3103448275862069, "acc_norm_stderr": 0.03855289616378948 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2619047619047619, "acc_stderr": 0.022644212615525214, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.022644212615525214 }, "hendrycksTest-formal_logic": { "acc": 0.29365079365079366, "acc_stderr": 0.040735243221471276, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.040735243221471276 }, "hendrycksTest-global_facts": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "hendrycksTest-high_school_biology": { "acc": 0.24193548387096775, "acc_stderr": 0.024362599693031086, "acc_norm": 0.24193548387096775, "acc_norm_stderr": 0.024362599693031086 }, "hendrycksTest-high_school_chemistry": { "acc": 0.15763546798029557, "acc_stderr": 0.025639014131172404, "acc_norm": 0.15763546798029557, "acc_norm_stderr": 0.025639014131172404 }, "hendrycksTest-high_school_computer_science": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "hendrycksTest-high_school_european_history": { "acc": 0.2909090909090909, "acc_stderr": 0.03546563019624335, "acc_norm": 0.2909090909090909, "acc_norm_stderr": 0.03546563019624335 }, "hendrycksTest-high_school_geography": { "acc": 0.2222222222222222, "acc_stderr": 0.02962022787479047, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.02962022787479047 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.21243523316062177, "acc_stderr": 0.029519282616817234, "acc_norm": 0.21243523316062177, "acc_norm_stderr": 0.029519282616817234 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.24358974358974358, "acc_stderr": 0.02176373368417393, "acc_norm": 0.24358974358974358, "acc_norm_stderr": 0.02176373368417393 }, "hendrycksTest-high_school_mathematics": { "acc": 0.25555555555555554, "acc_stderr": 0.02659393910184407, "acc_norm": 0.25555555555555554, "acc_norm_stderr": 0.02659393910184407 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.226890756302521, "acc_stderr": 0.027205371538279496, "acc_norm": 0.226890756302521, "acc_norm_stderr": 0.027205371538279496 }, "hendrycksTest-high_school_physics": { "acc": 0.2913907284768212, "acc_stderr": 0.037101857261199946, "acc_norm": 0.2913907284768212, "acc_norm_stderr": 0.037101857261199946 }, "hendrycksTest-high_school_psychology": { "acc": 0.22201834862385322, "acc_stderr": 0.01781884956479661, "acc_norm": 0.22201834862385322, "acc_norm_stderr": 0.01781884956479661 }, "hendrycksTest-high_school_statistics": { "acc": 0.2638888888888889, "acc_stderr": 0.030058202704309846, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.030058202704309846 }, "hendrycksTest-high_school_us_history": { "acc": 0.29901960784313725, "acc_stderr": 0.03213325717373616, "acc_norm": 0.29901960784313725, "acc_norm_stderr": 0.03213325717373616 }, "hendrycksTest-high_school_world_history": { "acc": 0.29535864978902954, "acc_stderr": 0.029696338713422886, "acc_norm": 0.29535864978902954, "acc_norm_stderr": 0.029696338713422886 }, "hendrycksTest-human_aging": { "acc": 0.27802690582959644, "acc_stderr": 0.030069584874494033, "acc_norm": 0.27802690582959644, "acc_norm_stderr": 0.030069584874494033 }, "hendrycksTest-human_sexuality": { "acc": 0.29770992366412213, "acc_stderr": 0.04010358942462203, "acc_norm": 0.29770992366412213, "acc_norm_stderr": 0.04010358942462203 }, "hendrycksTest-international_law": { "acc": 0.2892561983471074, "acc_stderr": 0.04139112727635464, "acc_norm": 0.2892561983471074, "acc_norm_stderr": 0.04139112727635464 }, "hendrycksTest-jurisprudence": { "acc": 0.28703703703703703, "acc_stderr": 0.043733130409147614, "acc_norm": 0.28703703703703703, "acc_norm_stderr": 0.043733130409147614 }, "hendrycksTest-logical_fallacies": { "acc": 0.22699386503067484, "acc_stderr": 0.032910995786157686, "acc_norm": 0.22699386503067484, "acc_norm_stderr": 0.032910995786157686 }, "hendrycksTest-machine_learning": { "acc": 0.2767857142857143, "acc_stderr": 0.04246624336697625, "acc_norm": 0.2767857142857143, "acc_norm_stderr": 0.04246624336697625 }, "hendrycksTest-management": { "acc": 0.18446601941747573, "acc_stderr": 0.03840423627288276, "acc_norm": 0.18446601941747573, "acc_norm_stderr": 0.03840423627288276 }, "hendrycksTest-marketing": { "acc": 0.2948717948717949, "acc_stderr": 0.029872577708891148, "acc_norm": 0.2948717948717949, "acc_norm_stderr": 0.029872577708891148 }, "hendrycksTest-medical_genetics": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "hendrycksTest-miscellaneous": { "acc": 0.30779054916985954, "acc_stderr": 0.016506045045155637, "acc_norm": 0.30779054916985954, "acc_norm_stderr": 0.016506045045155637 }, "hendrycksTest-moral_disputes": { "acc": 0.30346820809248554, "acc_stderr": 0.024752411960917202, "acc_norm": 0.30346820809248554, "acc_norm_stderr": 0.024752411960917202 }, "hendrycksTest-moral_scenarios": { "acc": 0.24916201117318434, "acc_stderr": 0.014465893829859923, "acc_norm": 0.24916201117318434, "acc_norm_stderr": 0.014465893829859923 }, "hendrycksTest-nutrition": { "acc": 0.2549019607843137, "acc_stderr": 0.02495418432487991, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.02495418432487991 }, "hendrycksTest-philosophy": { "acc": 0.34726688102893893, "acc_stderr": 0.027040745502307336, "acc_norm": 0.34726688102893893, "acc_norm_stderr": 0.027040745502307336 }, "hendrycksTest-prehistory": { "acc": 0.29012345679012347, "acc_stderr": 0.025251173936495012, "acc_norm": 0.29012345679012347, "acc_norm_stderr": 0.025251173936495012 }, "hendrycksTest-professional_accounting": { "acc": 0.30141843971631205, "acc_stderr": 0.02737412888263115, "acc_norm": 0.30141843971631205, "acc_norm_stderr": 0.02737412888263115 }, "hendrycksTest-professional_law": { "acc": 0.2816166883963494, "acc_stderr": 0.011487783272786696, "acc_norm": 0.2816166883963494, "acc_norm_stderr": 0.011487783272786696 }, "hendrycksTest-professional_medicine": { "acc": 0.1948529411764706, "acc_stderr": 0.024060599423487428, "acc_norm": 0.1948529411764706, "acc_norm_stderr": 0.024060599423487428 }, "hendrycksTest-professional_psychology": { "acc": 0.30718954248366015, "acc_stderr": 0.018663359671463653, "acc_norm": 0.30718954248366015, "acc_norm_stderr": 0.018663359671463653 }, "hendrycksTest-public_relations": { "acc": 0.2727272727272727, "acc_stderr": 0.04265792110940588, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.04265792110940588 }, "hendrycksTest-security_studies": { "acc": 0.2, "acc_stderr": 0.025607375986579153, "acc_norm": 0.2, "acc_norm_stderr": 0.025607375986579153 }, "hendrycksTest-sociology": { "acc": 0.24875621890547264, "acc_stderr": 0.030567675938916707, "acc_norm": 0.24875621890547264, "acc_norm_stderr": 0.030567675938916707 }, "hendrycksTest-us_foreign_policy": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "hendrycksTest-virology": { "acc": 0.2710843373493976, "acc_stderr": 0.03460579907553027, "acc_norm": 0.2710843373493976, "acc_norm_stderr": 0.03460579907553027 }, "hendrycksTest-world_religions": { "acc": 0.3742690058479532, "acc_stderr": 0.03711601185389481, "acc_norm": 0.3742690058479532, "acc_norm_stderr": 0.03711601185389481 } }, "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_359", "num_fewshot": 5, "batch_size": "1", "batch_sizes": [], "device": null, "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }