{ "results": { "hendrycksTest-abstract_algebra": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "hendrycksTest-anatomy": { "acc": 0.4666666666666667, "acc_stderr": 0.043097329010363554, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.043097329010363554 }, "hendrycksTest-astronomy": { "acc": 0.39473684210526316, "acc_stderr": 0.039777499346220734, "acc_norm": 0.39473684210526316, "acc_norm_stderr": 0.039777499346220734 }, "hendrycksTest-business_ethics": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "hendrycksTest-clinical_knowledge": { "acc": 0.47547169811320755, "acc_stderr": 0.030735822206205608, "acc_norm": 0.47547169811320755, "acc_norm_stderr": 0.030735822206205608 }, "hendrycksTest-college_biology": { "acc": 0.4583333333333333, "acc_stderr": 0.04166666666666666, "acc_norm": 0.4583333333333333, "acc_norm_stderr": 0.04166666666666666 }, "hendrycksTest-college_chemistry": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "hendrycksTest-college_computer_science": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "hendrycksTest-college_mathematics": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "hendrycksTest-college_medicine": { "acc": 0.4046242774566474, "acc_stderr": 0.03742461193887248, "acc_norm": 0.4046242774566474, "acc_norm_stderr": 0.03742461193887248 }, "hendrycksTest-college_physics": { "acc": 0.24509803921568626, "acc_stderr": 0.042801058373643966, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.042801058373643966 }, "hendrycksTest-computer_security": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "hendrycksTest-conceptual_physics": { "acc": 0.40425531914893614, "acc_stderr": 0.03208115750788684, "acc_norm": 0.40425531914893614, "acc_norm_stderr": 0.03208115750788684 }, "hendrycksTest-econometrics": { "acc": 0.3157894736842105, "acc_stderr": 0.043727482902780064, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.043727482902780064 }, "hendrycksTest-electrical_engineering": { "acc": 0.4413793103448276, "acc_stderr": 0.04137931034482757, "acc_norm": 0.4413793103448276, "acc_norm_stderr": 0.04137931034482757 }, "hendrycksTest-elementary_mathematics": { "acc": 0.2830687830687831, "acc_stderr": 0.023201392938194974, "acc_norm": 0.2830687830687831, "acc_norm_stderr": 0.023201392938194974 }, "hendrycksTest-formal_logic": { "acc": 0.23015873015873015, "acc_stderr": 0.037649508797906045, "acc_norm": 0.23015873015873015, "acc_norm_stderr": 0.037649508797906045 }, "hendrycksTest-global_facts": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "hendrycksTest-high_school_biology": { "acc": 0.47419354838709676, "acc_stderr": 0.028406095057653326, "acc_norm": 0.47419354838709676, "acc_norm_stderr": 0.028406095057653326 }, "hendrycksTest-high_school_chemistry": { "acc": 0.3251231527093596, "acc_stderr": 0.032957975663112704, "acc_norm": 0.3251231527093596, "acc_norm_stderr": 0.032957975663112704 }, "hendrycksTest-high_school_computer_science": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "hendrycksTest-high_school_european_history": { "acc": 0.6363636363636364, "acc_stderr": 0.03756335775187897, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.03756335775187897 }, "hendrycksTest-high_school_geography": { "acc": 0.5404040404040404, "acc_stderr": 0.035507024651313425, "acc_norm": 0.5404040404040404, "acc_norm_stderr": 0.035507024651313425 }, "hendrycksTest-high_school_government_and_politics": { "acc": 0.6269430051813472, "acc_stderr": 0.03490205592048573, "acc_norm": 0.6269430051813472, "acc_norm_stderr": 0.03490205592048573 }, "hendrycksTest-high_school_macroeconomics": { "acc": 0.41025641025641024, "acc_stderr": 0.024939313906940784, "acc_norm": 0.41025641025641024, "acc_norm_stderr": 0.024939313906940784 }, "hendrycksTest-high_school_mathematics": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085622, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934804085622 }, "hendrycksTest-high_school_microeconomics": { "acc": 0.42436974789915966, "acc_stderr": 0.03210479051015776, "acc_norm": 0.42436974789915966, "acc_norm_stderr": 0.03210479051015776 }, "hendrycksTest-high_school_physics": { "acc": 0.271523178807947, "acc_stderr": 0.03631329803969653, "acc_norm": 0.271523178807947, "acc_norm_stderr": 0.03631329803969653 }, "hendrycksTest-high_school_psychology": { "acc": 0.618348623853211, "acc_stderr": 0.020828148517022582, "acc_norm": 0.618348623853211, "acc_norm_stderr": 0.020828148517022582 }, "hendrycksTest-high_school_statistics": { "acc": 0.27314814814814814, "acc_stderr": 0.03038805130167812, "acc_norm": 0.27314814814814814, "acc_norm_stderr": 0.03038805130167812 }, "hendrycksTest-high_school_us_history": { "acc": 0.6470588235294118, "acc_stderr": 0.03354092437591518, "acc_norm": 0.6470588235294118, "acc_norm_stderr": 0.03354092437591518 }, "hendrycksTest-high_school_world_history": { "acc": 0.6371308016877637, "acc_stderr": 0.03129920825530213, "acc_norm": 0.6371308016877637, "acc_norm_stderr": 0.03129920825530213 }, "hendrycksTest-human_aging": { "acc": 0.5560538116591929, "acc_stderr": 0.03334625674242728, "acc_norm": 0.5560538116591929, "acc_norm_stderr": 0.03334625674242728 }, "hendrycksTest-human_sexuality": { "acc": 0.549618320610687, "acc_stderr": 0.04363643698524779, "acc_norm": 0.549618320610687, "acc_norm_stderr": 0.04363643698524779 }, "hendrycksTest-international_law": { "acc": 0.628099173553719, "acc_stderr": 0.04412015806624504, "acc_norm": 0.628099173553719, "acc_norm_stderr": 0.04412015806624504 }, "hendrycksTest-jurisprudence": { "acc": 0.48148148148148145, "acc_stderr": 0.04830366024635331, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.04830366024635331 }, "hendrycksTest-logical_fallacies": { "acc": 0.5214723926380368, "acc_stderr": 0.03924746876751129, "acc_norm": 0.5214723926380368, "acc_norm_stderr": 0.03924746876751129 }, "hendrycksTest-machine_learning": { "acc": 0.42857142857142855, "acc_stderr": 0.04697113923010212, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04697113923010212 }, "hendrycksTest-management": { "acc": 0.5242718446601942, "acc_stderr": 0.049449010929737795, "acc_norm": 0.5242718446601942, "acc_norm_stderr": 0.049449010929737795 }, "hendrycksTest-marketing": { "acc": 0.7094017094017094, "acc_stderr": 0.02974504857267408, "acc_norm": 0.7094017094017094, "acc_norm_stderr": 0.02974504857267408 }, "hendrycksTest-medical_genetics": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "hendrycksTest-miscellaneous": { "acc": 0.6194125159642401, "acc_stderr": 0.017362564126075414, "acc_norm": 0.6194125159642401, "acc_norm_stderr": 0.017362564126075414 }, "hendrycksTest-moral_disputes": { "acc": 0.5260115606936416, "acc_stderr": 0.026882643434022885, "acc_norm": 0.5260115606936416, "acc_norm_stderr": 0.026882643434022885 }, "hendrycksTest-moral_scenarios": { "acc": 0.23798882681564246, "acc_stderr": 0.014242630070574911, "acc_norm": 0.23798882681564246, "acc_norm_stderr": 0.014242630070574911 }, "hendrycksTest-nutrition": { "acc": 0.4803921568627451, "acc_stderr": 0.028607893699576063, "acc_norm": 0.4803921568627451, "acc_norm_stderr": 0.028607893699576063 }, "hendrycksTest-philosophy": { "acc": 0.5594855305466238, "acc_stderr": 0.028196400574197426, "acc_norm": 0.5594855305466238, "acc_norm_stderr": 0.028196400574197426 }, "hendrycksTest-prehistory": { "acc": 0.5462962962962963, "acc_stderr": 0.0277012284685426, "acc_norm": 0.5462962962962963, "acc_norm_stderr": 0.0277012284685426 }, "hendrycksTest-professional_accounting": { "acc": 0.36524822695035464, "acc_stderr": 0.02872386385328128, "acc_norm": 0.36524822695035464, "acc_norm_stderr": 0.02872386385328128 }, "hendrycksTest-professional_law": { "acc": 0.36571056062581486, "acc_stderr": 0.012301028188840567, "acc_norm": 0.36571056062581486, "acc_norm_stderr": 0.012301028188840567 }, "hendrycksTest-professional_medicine": { "acc": 0.4411764705882353, "acc_stderr": 0.030161911930767105, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.030161911930767105 }, "hendrycksTest-professional_psychology": { "acc": 0.44281045751633985, "acc_stderr": 0.020095083154577347, "acc_norm": 0.44281045751633985, "acc_norm_stderr": 0.020095083154577347 }, "hendrycksTest-public_relations": { "acc": 0.5727272727272728, "acc_stderr": 0.04738198703545483, "acc_norm": 0.5727272727272728, "acc_norm_stderr": 0.04738198703545483 }, "hendrycksTest-security_studies": { "acc": 0.49795918367346936, "acc_stderr": 0.0320089533497105, "acc_norm": 0.49795918367346936, "acc_norm_stderr": 0.0320089533497105 }, "hendrycksTest-sociology": { "acc": 0.6318407960199005, "acc_stderr": 0.03410410565495301, "acc_norm": 0.6318407960199005, "acc_norm_stderr": 0.03410410565495301 }, "hendrycksTest-us_foreign_policy": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "hendrycksTest-virology": { "acc": 0.4036144578313253, "acc_stderr": 0.038194861407583984, "acc_norm": 0.4036144578313253, "acc_norm_stderr": 0.038194861407583984 }, "hendrycksTest-world_religions": { "acc": 0.6432748538011696, "acc_stderr": 0.03674013002860954, "acc_norm": 0.6432748538011696, "acc_norm_stderr": 0.03674013002860954 } }, "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": "sparseml", "model_args": "pretrained=/nm/drive1/alexandre/zoo/llama2-7b-ultrachat200k_llama2_pretrain-base/training,dtype=float32", "num_fewshot": 5, "batch_size": "4", "batch_sizes": [], "device": "cuda:7", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }