{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "hendrycksTest-anatomy": { "acc": 0.34074074074074073, "acc_stderr": 0.04094376269996793, "acc_norm": 0.34074074074074073, "acc_norm_stderr": 0.04094376269996793 }, "hendrycksTest-astronomy": { "acc": 0.2565789473684211, "acc_stderr": 0.035541803680256896, "acc_norm": 0.2565789473684211, "acc_norm_stderr": 0.035541803680256896 }, "hendrycksTest-business_ethics": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "hendrycksTest-clinical_knowledge": { "acc": 0.30943396226415093, "acc_stderr": 0.028450154794118627, "acc_norm": 0.30943396226415093, "acc_norm_stderr": 0.028450154794118627 }, "hendrycksTest-college_biology": { "acc": 0.3055555555555556, "acc_stderr": 0.03852084696008534, "acc_norm": 0.3055555555555556, "acc_norm_stderr": 0.03852084696008534 }, "hendrycksTest-college_chemistry": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "hendrycksTest-college_computer_science": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "hendrycksTest-college_mathematics": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "hendrycksTest-college_medicine": { "acc": 0.2658959537572254, "acc_stderr": 0.03368762932259431, "acc_norm": 0.2658959537572254, "acc_norm_stderr": 0.03368762932259431 }, "hendrycksTest-college_physics": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "hendrycksTest-computer_security": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "hendrycksTest-conceptual_physics": { "acc": 0.3021276595744681, "acc_stderr": 0.030017554471880554, "acc_norm": 0.3021276595744681, "acc_norm_stderr": 0.030017554471880554 }, "hendrycksTest-econometrics": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "hendrycksTest-electrical_engineering": { "acc": 0.2896551724137931, "acc_stderr": 0.037800192304380135, "acc_norm": 0.2896551724137931, "acc_norm_stderr": 0.037800192304380135 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2777777777777778, "acc_stderr": 0.02306818884826111, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.02306818884826111 }, "hendrycksTest-formal_logic": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "hendrycksTest-global_facts": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "hendrycksTest-high_school_biology": { "acc": 0.27741935483870966, "acc_stderr": 0.025470196835900055, "acc_norm": 0.27741935483870966, "acc_norm_stderr": 0.025470196835900055 }, "hendrycksTest-high_school_chemistry": { "acc": 0.2660098522167488, "acc_stderr": 0.031089826002937523, "acc_norm": 0.2660098522167488, "acc_norm_stderr": 0.031089826002937523 }, "hendrycksTest-high_school_computer_science": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "hendrycksTest-high_school_european_history": { "acc": 0.3151515151515151, "acc_stderr": 0.0362773057502241, "acc_norm": 0.3151515151515151, "acc_norm_stderr": 0.0362773057502241 }, "hendrycksTest-high_school_geography": { "acc": 0.2676767676767677, "acc_stderr": 0.03154449888270286, "acc_norm": 0.2676767676767677, "acc_norm_stderr": 0.03154449888270286 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.23834196891191708, "acc_stderr": 0.030748905363909892, "acc_norm": 0.23834196891191708, "acc_norm_stderr": 0.030748905363909892 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.24358974358974358, "acc_stderr": 0.021763733684173926, "acc_norm": 0.24358974358974358, "acc_norm_stderr": 0.021763733684173926 }, "hendrycksTest-high_school_mathematics": { "acc": 0.23703703703703705, "acc_stderr": 0.0259288761327661, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.0259288761327661 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.2605042016806723, "acc_stderr": 0.02851025151234192, "acc_norm": 0.2605042016806723, "acc_norm_stderr": 0.02851025151234192 }, "hendrycksTest-high_school_physics": { "acc": 0.2980132450331126, "acc_stderr": 0.037345356767871984, "acc_norm": 0.2980132450331126, "acc_norm_stderr": 0.037345356767871984 }, "hendrycksTest-high_school_psychology": { "acc": 0.3192660550458716, "acc_stderr": 0.01998782906975001, "acc_norm": 0.3192660550458716, "acc_norm_stderr": 0.01998782906975001 }, "hendrycksTest-high_school_statistics": { "acc": 0.28703703703703703, "acc_stderr": 0.030851992993257013, "acc_norm": 0.28703703703703703, "acc_norm_stderr": 0.030851992993257013 }, "hendrycksTest-high_school_us_history": { "acc": 0.28921568627450983, "acc_stderr": 0.03182231867647554, "acc_norm": 0.28921568627450983, "acc_norm_stderr": 0.03182231867647554 }, "hendrycksTest-high_school_world_history": { "acc": 0.2911392405063291, "acc_stderr": 0.029571601065753374, "acc_norm": 0.2911392405063291, "acc_norm_stderr": 0.029571601065753374 }, "hendrycksTest-human_aging": { "acc": 0.30493273542600896, "acc_stderr": 0.030898610882477515, "acc_norm": 0.30493273542600896, "acc_norm_stderr": 0.030898610882477515 }, "hendrycksTest-human_sexuality": { "acc": 0.29770992366412213, "acc_stderr": 0.04010358942462202, "acc_norm": 0.29770992366412213, "acc_norm_stderr": 0.04010358942462202 }, "hendrycksTest-international_law": { "acc": 0.34710743801652894, "acc_stderr": 0.04345724570292534, "acc_norm": 0.34710743801652894, "acc_norm_stderr": 0.04345724570292534 }, "hendrycksTest-jurisprudence": { "acc": 0.3333333333333333, "acc_stderr": 0.04557239513497751, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04557239513497751 }, "hendrycksTest-logical_fallacies": { "acc": 0.22699386503067484, "acc_stderr": 0.03291099578615769, "acc_norm": 0.22699386503067484, "acc_norm_stderr": 0.03291099578615769 }, "hendrycksTest-machine_learning": { "acc": 0.2767857142857143, "acc_stderr": 0.042466243366976256, "acc_norm": 0.2767857142857143, "acc_norm_stderr": 0.042466243366976256 }, "hendrycksTest-management": { "acc": 0.2524271844660194, "acc_stderr": 0.04301250399690875, "acc_norm": 0.2524271844660194, "acc_norm_stderr": 0.04301250399690875 }, "hendrycksTest-marketing": { "acc": 0.3333333333333333, "acc_stderr": 0.030882736974138642, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.030882736974138642 }, "hendrycksTest-medical_genetics": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "hendrycksTest-miscellaneous": { "acc": 0.3128991060025543, "acc_stderr": 0.01658093594030407, "acc_norm": 0.3128991060025543, "acc_norm_stderr": 0.01658093594030407 }, "hendrycksTest-moral_disputes": { "acc": 0.3265895953757225, "acc_stderr": 0.025248264774242832, "acc_norm": 0.3265895953757225, "acc_norm_stderr": 0.025248264774242832 }, "hendrycksTest-moral_scenarios": { "acc": 0.2424581005586592, "acc_stderr": 0.014333522059217889, "acc_norm": 0.2424581005586592, "acc_norm_stderr": 0.014333522059217889 }, "hendrycksTest-nutrition": { "acc": 0.3137254901960784, "acc_stderr": 0.026568921015457155, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.026568921015457155 }, "hendrycksTest-philosophy": { "acc": 0.31189710610932475, "acc_stderr": 0.02631185807185416, "acc_norm": 0.31189710610932475, "acc_norm_stderr": 0.02631185807185416 }, "hendrycksTest-prehistory": { "acc": 0.2808641975308642, "acc_stderr": 0.025006469755799208, "acc_norm": 0.2808641975308642, "acc_norm_stderr": 0.025006469755799208 }, "hendrycksTest-professional_accounting": { "acc": 0.2695035460992908, "acc_stderr": 0.026469036818590638, "acc_norm": 0.2695035460992908, "acc_norm_stderr": 0.026469036818590638 }, "hendrycksTest-professional_law": { "acc": 0.28292046936114734, "acc_stderr": 0.011503891323188974, "acc_norm": 0.28292046936114734, "acc_norm_stderr": 0.011503891323188974 }, "hendrycksTest-professional_medicine": { "acc": 0.21691176470588236, "acc_stderr": 0.025035845227711254, "acc_norm": 0.21691176470588236, "acc_norm_stderr": 0.025035845227711254 }, "hendrycksTest-professional_psychology": { "acc": 0.3104575163398693, "acc_stderr": 0.01871806705262322, "acc_norm": 0.3104575163398693, "acc_norm_stderr": 0.01871806705262322 }, "hendrycksTest-public_relations": { "acc": 0.39090909090909093, "acc_stderr": 0.04673752333670237, "acc_norm": 0.39090909090909093, "acc_norm_stderr": 0.04673752333670237 }, "hendrycksTest-security_studies": { "acc": 0.2693877551020408, "acc_stderr": 0.02840125202902294, "acc_norm": 0.2693877551020408, "acc_norm_stderr": 0.02840125202902294 }, "hendrycksTest-sociology": { "acc": 0.3034825870646766, "acc_stderr": 0.03251006816458617, "acc_norm": 0.3034825870646766, "acc_norm_stderr": 0.03251006816458617 }, "hendrycksTest-us_foreign_policy": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "hendrycksTest-virology": { "acc": 0.3373493975903614, "acc_stderr": 0.03680783690727581, "acc_norm": 0.3373493975903614, "acc_norm_stderr": 0.03680783690727581 }, "hendrycksTest-world_religions": { "acc": 0.3391812865497076, "acc_stderr": 0.03631053496488905, "acc_norm": 0.3391812865497076, "acc_norm_stderr": 0.03631053496488905 } }, "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/ckpt_351", "num_fewshot": 5, "batch_size": "8", "batch_sizes": [], "device": null, "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }