{ "results": { "hendrycksTest-high_school_geography": { "acc": 0.4292929292929293, "acc_stderr": 0.035265527246011986, "acc_norm": 0.36363636363636365, "acc_norm_stderr": 0.03427308652999934 }, "hendrycksTest-philosophy": { "acc": 0.40192926045016075, "acc_stderr": 0.027846476005930477, "acc_norm": 0.3536977491961415, "acc_norm_stderr": 0.02715520810320088 }, "hendrycksTest-world_religions": { "acc": 0.6257309941520468, "acc_stderr": 0.03711601185389481, "acc_norm": 0.5146198830409356, "acc_norm_stderr": 0.038331852752130254 }, "hendrycksTest-college_biology": { "acc": 0.3194444444444444, "acc_stderr": 0.03899073687357335, "acc_norm": 0.2916666666666667, "acc_norm_stderr": 0.03800968060554858 }, "hendrycksTest-electrical_engineering": { "acc": 0.3586206896551724, "acc_stderr": 0.03996629574876719, "acc_norm": 0.32413793103448274, "acc_norm_stderr": 0.03900432069185554 }, "hendrycksTest-global_facts": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206824 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.48186528497409326, "acc_stderr": 0.03606065001832917, "acc_norm": 0.37305699481865284, "acc_norm_stderr": 0.03490205592048573 }, "hendrycksTest-moral_scenarios": { "acc": 0.2759776536312849, "acc_stderr": 0.014950103002475353, "acc_norm": 0.27262569832402234, "acc_norm_stderr": 0.014893391735249588 }, "hendrycksTest-econometrics": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.0414243971948936 }, "hendrycksTest-international_law": { "acc": 0.3884297520661157, "acc_stderr": 0.04449270350068382, "acc_norm": 0.5785123966942148, "acc_norm_stderr": 0.045077322787750874 }, "hendrycksTest-us_foreign_policy": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.31794871794871793, "acc_stderr": 0.02361088430892786, "acc_norm": 0.30256410256410254, "acc_norm_stderr": 0.023290888053772742 }, "hendrycksTest-virology": { "acc": 0.39759036144578314, "acc_stderr": 0.038099730845402184, "acc_norm": 0.2891566265060241, "acc_norm_stderr": 0.035294868015111155 }, "hendrycksTest-high_school_mathematics": { "acc": 0.22592592592592592, "acc_stderr": 0.025497532639609542, "acc_norm": 0.3074074074074074, "acc_norm_stderr": 0.02813325257881564 }, "hendrycksTest-clinical_knowledge": { "acc": 0.3886792452830189, "acc_stderr": 0.03000048544867599, "acc_norm": 0.38113207547169814, "acc_norm_stderr": 0.029890609686286627 }, "hendrycksTest-professional_psychology": { "acc": 0.3839869281045752, "acc_stderr": 0.01967580813528152, "acc_norm": 0.29901960784313725, "acc_norm_stderr": 0.01852175621542302 }, "hendrycksTest-formal_logic": { "acc": 0.30952380952380953, "acc_stderr": 0.04134913018303316, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.042639068927951315 }, "hendrycksTest-management": { "acc": 0.4854368932038835, "acc_stderr": 0.04948637324026637, "acc_norm": 0.36893203883495146, "acc_norm_stderr": 0.0477761518115674 }, "hendrycksTest-human_sexuality": { "acc": 0.5114503816793893, "acc_stderr": 0.043841400240780176, "acc_norm": 0.366412213740458, "acc_norm_stderr": 0.042258754519696386 }, "hendrycksTest-high_school_world_history": { "acc": 0.3924050632911392, "acc_stderr": 0.03178471874564729, "acc_norm": 0.33755274261603374, "acc_norm_stderr": 0.030781549102026216 }, "hendrycksTest-medical_genetics": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "hendrycksTest-computer_security": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "hendrycksTest-miscellaneous": { "acc": 0.5836526181353767, "acc_stderr": 0.0176279480304303, "acc_norm": 0.3895274584929757, "acc_norm_stderr": 0.017438082556264597 }, "hendrycksTest-public_relations": { "acc": 0.39090909090909093, "acc_stderr": 0.046737523336702384, "acc_norm": 0.22727272727272727, "acc_norm_stderr": 0.040139645540727735 }, "hendrycksTest-college_physics": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171453, "acc_norm": 0.3235294117647059, "acc_norm_stderr": 0.046550104113196177 }, "hendrycksTest-professional_accounting": { "acc": 0.30141843971631205, "acc_stderr": 0.02737412888263115, "acc_norm": 0.29432624113475175, "acc_norm_stderr": 0.027187127011503793 }, "hendrycksTest-logical_fallacies": { "acc": 0.3803680981595092, "acc_stderr": 0.03814269893261837, "acc_norm": 0.3496932515337423, "acc_norm_stderr": 0.037466683254700206 }, "hendrycksTest-business_ethics": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "hendrycksTest-high_school_chemistry": { "acc": 0.2512315270935961, "acc_stderr": 0.030516530732694436, "acc_norm": 0.2955665024630542, "acc_norm_stderr": 0.03210494433751458 }, "hendrycksTest-astronomy": { "acc": 0.45394736842105265, "acc_stderr": 0.04051646342874143, "acc_norm": 0.4605263157894737, "acc_norm_stderr": 0.04056242252249033 }, "hendrycksTest-high_school_us_history": { "acc": 0.4264705882352941, "acc_stderr": 0.03471157907953424, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.032566854844603886 }, "hendrycksTest-college_chemistry": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "hendrycksTest-abstract_algebra": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "hendrycksTest-moral_disputes": { "acc": 0.36416184971098264, "acc_stderr": 0.025906632631016117, "acc_norm": 0.33236994219653176, "acc_norm_stderr": 0.02536116874968821 }, "hendrycksTest-college_computer_science": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "hendrycksTest-professional_law": { "acc": 0.2966101694915254, "acc_stderr": 0.011665946586082849, "acc_norm": 0.28552803129074317, "acc_norm_stderr": 0.011535751586665664 }, "hendrycksTest-college_mathematics": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.3865546218487395, "acc_stderr": 0.0316314580755238, "acc_norm": 0.36554621848739494, "acc_norm_stderr": 0.0312821770636846 }, "hendrycksTest-high_school_european_history": { "acc": 0.40606060606060607, "acc_stderr": 0.03834816355401181, "acc_norm": 0.3696969696969697, "acc_norm_stderr": 0.03769430314512568 }, "hendrycksTest-high_school_biology": { "acc": 0.3580645161290323, "acc_stderr": 0.027273890594300642, "acc_norm": 0.3580645161290323, "acc_norm_stderr": 0.02727389059430063 }, "hendrycksTest-security_studies": { "acc": 0.40816326530612246, "acc_stderr": 0.03146465712827424, "acc_norm": 0.31020408163265306, "acc_norm_stderr": 0.029613459872484375 }, "hendrycksTest-high_school_psychology": { "acc": 0.46605504587155966, "acc_stderr": 0.02138786335035399, "acc_norm": 0.30825688073394497, "acc_norm_stderr": 0.01979836669836726 }, "hendrycksTest-conceptual_physics": { "acc": 0.3276595744680851, "acc_stderr": 0.030683020843231004, "acc_norm": 0.2170212765957447, "acc_norm_stderr": 0.026947483121496228 }, "hendrycksTest-human_aging": { "acc": 0.3721973094170404, "acc_stderr": 0.03244305283008731, "acc_norm": 0.25112107623318386, "acc_norm_stderr": 0.02910522083322462 }, "hendrycksTest-prehistory": { "acc": 0.4012345679012346, "acc_stderr": 0.0272725828498398, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.02492200116888633 }, "hendrycksTest-sociology": { "acc": 0.47761194029850745, "acc_stderr": 0.035319879302087305, "acc_norm": 0.42786069651741293, "acc_norm_stderr": 0.03498541988407795 }, "hendrycksTest-marketing": { "acc": 0.6111111111111112, "acc_stderr": 0.031937057262002924, "acc_norm": 0.5042735042735043, "acc_norm_stderr": 0.03275489264382132 }, "hendrycksTest-high_school_computer_science": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "hendrycksTest-machine_learning": { "acc": 0.30357142857142855, "acc_stderr": 0.04364226155841044, "acc_norm": 0.26785714285714285, "acc_norm_stderr": 0.04203277291467762 }, "hendrycksTest-elementary_mathematics": { "acc": 0.3201058201058201, "acc_stderr": 0.024026846392873506, "acc_norm": 0.291005291005291, "acc_norm_stderr": 0.023393826500484865 }, "hendrycksTest-nutrition": { "acc": 0.3954248366013072, "acc_stderr": 0.027996723180631435, "acc_norm": 0.43790849673202614, "acc_norm_stderr": 0.028408302020332694 }, "hendrycksTest-anatomy": { "acc": 0.3851851851851852, "acc_stderr": 0.042039210401562783, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.03885004245800254 }, "hendrycksTest-jurisprudence": { "acc": 0.4351851851851852, "acc_stderr": 0.04792898170907062, "acc_norm": 0.5, "acc_norm_stderr": 0.04833682445228318 }, "hendrycksTest-college_medicine": { "acc": 0.37572254335260113, "acc_stderr": 0.036928207672648664, "acc_norm": 0.3063583815028902, "acc_norm_stderr": 0.03514942551267439 }, "hendrycksTest-high_school_statistics": { "acc": 0.3425925925925926, "acc_stderr": 0.03236585252602156, "acc_norm": 0.3425925925925926, "acc_norm_stderr": 0.03236585252602156 }, "hendrycksTest-high_school_physics": { "acc": 0.2052980132450331, "acc_stderr": 0.03297986648473834, "acc_norm": 0.271523178807947, "acc_norm_stderr": 0.036313298039696525 }, "hendrycksTest-professional_medicine": { "acc": 0.3382352941176471, "acc_stderr": 0.028739328513983576, "acc_norm": 0.27941176470588236, "acc_norm_stderr": 0.027257202606114948 } }, "versions": { "hendrycksTest-high_school_geography": 0, "hendrycksTest-philosophy": 0, "hendrycksTest-world_religions": 0, "hendrycksTest-college_biology": 0, "hendrycksTest-electrical_engineering": 0, "hendrycksTest-global_facts": 0, "hendrycksTest-high_school_government_and_politics": 0, "hendrycksTest-moral_scenarios": 0, "hendrycksTest-econometrics": 0, "hendrycksTest-international_law": 0, "hendrycksTest-us_foreign_policy": 0, "hendrycksTest-high_school_macroeconomics": 0, "hendrycksTest-virology": 0, "hendrycksTest-high_school_mathematics": 0, "hendrycksTest-clinical_knowledge": 0, "hendrycksTest-professional_psychology": 0, "hendrycksTest-formal_logic": 0, "hendrycksTest-management": 0, "hendrycksTest-human_sexuality": 0, "hendrycksTest-high_school_world_history": 0, "hendrycksTest-medical_genetics": 0, "hendrycksTest-computer_security": 0, "hendrycksTest-miscellaneous": 0, "hendrycksTest-public_relations": 0, "hendrycksTest-college_physics": 0, "hendrycksTest-professional_accounting": 0, "hendrycksTest-logical_fallacies": 0, "hendrycksTest-business_ethics": 0, "hendrycksTest-high_school_chemistry": 0, "hendrycksTest-astronomy": 0, "hendrycksTest-high_school_us_history": 0, "hendrycksTest-college_chemistry": 0, "hendrycksTest-abstract_algebra": 0, "hendrycksTest-moral_disputes": 0, "hendrycksTest-college_computer_science": 0, "hendrycksTest-professional_law": 0, "hendrycksTest-college_mathematics": 0, "hendrycksTest-high_school_microeconomics": 0, "hendrycksTest-high_school_european_history": 0, "hendrycksTest-high_school_biology": 0, "hendrycksTest-security_studies": 0, "hendrycksTest-high_school_psychology": 0, "hendrycksTest-conceptual_physics": 0, "hendrycksTest-human_aging": 0, "hendrycksTest-prehistory": 0, "hendrycksTest-sociology": 0, "hendrycksTest-marketing": 0, "hendrycksTest-high_school_computer_science": 0, "hendrycksTest-machine_learning": 0, "hendrycksTest-elementary_mathematics": 0, "hendrycksTest-nutrition": 0, "hendrycksTest-anatomy": 0, "hendrycksTest-jurisprudence": 0, "hendrycksTest-college_medicine": 0, "hendrycksTest-high_school_statistics": 0, "hendrycksTest-high_school_physics": 0, "hendrycksTest-professional_medicine": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=/gaueko1/hizkuntza-ereduak/LLaMA/lm/huggingface/7B,use_accelerate=True", "num_fewshot": 5, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }