{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.27, "acc_stderr": 0.044619604333847415, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847415 }, "hendrycksTest-anatomy": { "acc": 0.24444444444444444, "acc_stderr": 0.03712537833614865, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.03712537833614865 }, "hendrycksTest-astronomy": { "acc": 0.2565789473684211, "acc_stderr": 0.0355418036802569, "acc_norm": 0.2565789473684211, "acc_norm_stderr": 0.0355418036802569 }, "hendrycksTest-business_ethics": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "hendrycksTest-clinical_knowledge": { "acc": 0.33962264150943394, "acc_stderr": 0.029146904747798335, "acc_norm": 0.33962264150943394, "acc_norm_stderr": 0.029146904747798335 }, "hendrycksTest-college_biology": { "acc": 0.3194444444444444, "acc_stderr": 0.038990736873573344, "acc_norm": 0.3194444444444444, "acc_norm_stderr": 0.038990736873573344 }, "hendrycksTest-college_chemistry": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "hendrycksTest-college_computer_science": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "hendrycksTest-college_mathematics": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "hendrycksTest-college_medicine": { "acc": 0.27167630057803466, "acc_stderr": 0.03391750322321659, "acc_norm": 0.27167630057803466, "acc_norm_stderr": 0.03391750322321659 }, "hendrycksTest-college_physics": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617748, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617748 }, "hendrycksTest-computer_security": { "acc": 0.35, "acc_stderr": 0.04793724854411018, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411018 }, "hendrycksTest-conceptual_physics": { "acc": 0.3404255319148936, "acc_stderr": 0.030976692998534436, "acc_norm": 0.3404255319148936, "acc_norm_stderr": 0.030976692998534436 }, "hendrycksTest-econometrics": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "hendrycksTest-electrical_engineering": { "acc": 0.2896551724137931, "acc_stderr": 0.037800192304380135, "acc_norm": 0.2896551724137931, "acc_norm_stderr": 0.037800192304380135 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2671957671957672, "acc_stderr": 0.02278967314577656, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.02278967314577656 }, "hendrycksTest-formal_logic": { "acc": 0.29365079365079366, "acc_stderr": 0.040735243221471276, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.040735243221471276 }, "hendrycksTest-global_facts": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "hendrycksTest-high_school_biology": { "acc": 0.26129032258064516, "acc_stderr": 0.024993053397764826, "acc_norm": 0.26129032258064516, "acc_norm_stderr": 0.024993053397764826 }, "hendrycksTest-high_school_chemistry": { "acc": 0.2857142857142857, "acc_stderr": 0.03178529710642749, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.03178529710642749 }, "hendrycksTest-high_school_computer_science": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "hendrycksTest-high_school_european_history": { "acc": 0.3333333333333333, "acc_stderr": 0.03681050869161549, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.03681050869161549 }, "hendrycksTest-high_school_geography": { "acc": 0.2828282828282828, "acc_stderr": 0.0320877955878675, "acc_norm": 0.2828282828282828, "acc_norm_stderr": 0.0320877955878675 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.22279792746113988, "acc_stderr": 0.030031147977641545, "acc_norm": 0.22279792746113988, "acc_norm_stderr": 0.030031147977641545 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.23846153846153847, "acc_stderr": 0.021606294494647727, "acc_norm": 0.23846153846153847, "acc_norm_stderr": 0.021606294494647727 }, "hendrycksTest-high_school_mathematics": { "acc": 0.25925925925925924, "acc_stderr": 0.026719240783712173, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.026719240783712173 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.27310924369747897, "acc_stderr": 0.028942004040998167, "acc_norm": 0.27310924369747897, "acc_norm_stderr": 0.028942004040998167 }, "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": 0.3321100917431193, "acc_stderr": 0.02019268298542334, "acc_norm": 0.3321100917431193, "acc_norm_stderr": 0.02019268298542334 }, "hendrycksTest-high_school_statistics": { "acc": 0.24074074074074073, "acc_stderr": 0.029157522184605603, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.029157522184605603 }, "hendrycksTest-high_school_us_history": { "acc": 0.2696078431372549, "acc_stderr": 0.03114557065948678, "acc_norm": 0.2696078431372549, "acc_norm_stderr": 0.03114557065948678 }, "hendrycksTest-high_school_world_history": { "acc": 0.34177215189873417, "acc_stderr": 0.030874537537553617, "acc_norm": 0.34177215189873417, "acc_norm_stderr": 0.030874537537553617 }, "hendrycksTest-human_aging": { "acc": 0.2645739910313901, "acc_stderr": 0.02960510321703831, "acc_norm": 0.2645739910313901, "acc_norm_stderr": 0.02960510321703831 }, "hendrycksTest-human_sexuality": { "acc": 0.26717557251908397, "acc_stderr": 0.03880848301082396, "acc_norm": 0.26717557251908397, "acc_norm_stderr": 0.03880848301082396 }, "hendrycksTest-international_law": { "acc": 0.3305785123966942, "acc_stderr": 0.04294340845212095, "acc_norm": 0.3305785123966942, "acc_norm_stderr": 0.04294340845212095 }, "hendrycksTest-jurisprudence": { "acc": 0.2962962962962963, "acc_stderr": 0.044143436668549335, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.044143436668549335 }, "hendrycksTest-logical_fallacies": { "acc": 0.19631901840490798, "acc_stderr": 0.031207970394709215, "acc_norm": 0.19631901840490798, "acc_norm_stderr": 0.031207970394709215 }, "hendrycksTest-machine_learning": { "acc": 0.26785714285714285, "acc_stderr": 0.04203277291467764, "acc_norm": 0.26785714285714285, "acc_norm_stderr": 0.04203277291467764 }, "hendrycksTest-management": { "acc": 0.2815533980582524, "acc_stderr": 0.04453254836326469, "acc_norm": 0.2815533980582524, "acc_norm_stderr": 0.04453254836326469 }, "hendrycksTest-marketing": { "acc": 0.36752136752136755, "acc_stderr": 0.03158539157745635, "acc_norm": 0.36752136752136755, "acc_norm_stderr": 0.03158539157745635 }, "hendrycksTest-medical_genetics": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "hendrycksTest-miscellaneous": { "acc": 0.33205619412515963, "acc_stderr": 0.016841174655295735, "acc_norm": 0.33205619412515963, "acc_norm_stderr": 0.016841174655295735 }, "hendrycksTest-moral_disputes": { "acc": 0.33236994219653176, "acc_stderr": 0.025361168749688225, "acc_norm": 0.33236994219653176, "acc_norm_stderr": 0.025361168749688225 }, "hendrycksTest-moral_scenarios": { "acc": 0.23575418994413408, "acc_stderr": 0.014196375686290804, "acc_norm": 0.23575418994413408, "acc_norm_stderr": 0.014196375686290804 }, "hendrycksTest-nutrition": { "acc": 0.30392156862745096, "acc_stderr": 0.026336613469046647, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.026336613469046647 }, "hendrycksTest-philosophy": { "acc": 0.3022508038585209, "acc_stderr": 0.026082700695399662, "acc_norm": 0.3022508038585209, "acc_norm_stderr": 0.026082700695399662 }, "hendrycksTest-prehistory": { "acc": 0.2716049382716049, "acc_stderr": 0.02474862449053737, "acc_norm": 0.2716049382716049, "acc_norm_stderr": 0.02474862449053737 }, "hendrycksTest-professional_accounting": { "acc": 0.2765957446808511, "acc_stderr": 0.026684564340461004, "acc_norm": 0.2765957446808511, "acc_norm_stderr": 0.026684564340461004 }, "hendrycksTest-professional_law": { "acc": 0.26792698826597133, "acc_stderr": 0.01131134769063386, "acc_norm": 0.26792698826597133, "acc_norm_stderr": 0.01131134769063386 }, "hendrycksTest-professional_medicine": { "acc": 0.1875, "acc_stderr": 0.023709788253811766, "acc_norm": 0.1875, "acc_norm_stderr": 0.023709788253811766 }, "hendrycksTest-professional_psychology": { "acc": 0.3088235294117647, "acc_stderr": 0.018690850273595284, "acc_norm": 0.3088235294117647, "acc_norm_stderr": 0.018690850273595284 }, "hendrycksTest-public_relations": { "acc": 0.35454545454545455, "acc_stderr": 0.04582004841505416, "acc_norm": 0.35454545454545455, "acc_norm_stderr": 0.04582004841505416 }, "hendrycksTest-security_studies": { "acc": 0.20408163265306123, "acc_stderr": 0.02580128347509051, "acc_norm": 0.20408163265306123, "acc_norm_stderr": 0.02580128347509051 }, "hendrycksTest-sociology": { "acc": 0.2736318407960199, "acc_stderr": 0.03152439186555401, "acc_norm": 0.2736318407960199, "acc_norm_stderr": 0.03152439186555401 }, "hendrycksTest-us_foreign_policy": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "hendrycksTest-virology": { "acc": 0.3493975903614458, "acc_stderr": 0.03711725190740748, "acc_norm": 0.3493975903614458, "acc_norm_stderr": 0.03711725190740748 }, "hendrycksTest-world_religions": { "acc": 0.3508771929824561, "acc_stderr": 0.036602988340491624, "acc_norm": 0.3508771929824561, "acc_norm_stderr": 0.036602988340491624 } }, "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_358", "num_fewshot": 5, "batch_size": "1", "batch_sizes": [], "device": null, "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }