Amber / eval_mmlu.json
omkarenator's picture
Upload folder using huggingface_hub
e541d1a
Raw History Blame
14.2 kB
{
"results": {
"hendrycksTest-abstract_algebra": {
"acc": 0.29,
"acc_stderr": 0.04560480215720684,
"acc_norm": 0.29,
"acc_norm_stderr": 0.04560480215720684
},
"hendrycksTest-anatomy": {
"acc": 0.3333333333333333,
"acc_stderr": 0.04072314811876837,
"acc_norm": 0.3333333333333333,
"acc_norm_stderr": 0.04072314811876837
},
"hendrycksTest-astronomy": {
"acc": 0.2894736842105263,
"acc_stderr": 0.036906779861372814,
"acc_norm": 0.2894736842105263,
"acc_norm_stderr": 0.036906779861372814
},
"hendrycksTest-business_ethics": {
"acc": 0.35,
"acc_stderr": 0.047937248544110196,
"acc_norm": 0.35,
"acc_norm_stderr": 0.047937248544110196
},
"hendrycksTest-clinical_knowledge": {
"acc": 0.3169811320754717,
"acc_stderr": 0.028637235639800925,
"acc_norm": 0.3169811320754717,
"acc_norm_stderr": 0.028637235639800925
},
"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": 0.42,
"acc_stderr": 0.04960449637488583,
"acc_norm": 0.42,
"acc_norm_stderr": 0.04960449637488583
},
"hendrycksTest-college_mathematics": {
"acc": 0.25,
"acc_stderr": 0.04351941398892446,
"acc_norm": 0.25,
"acc_norm_stderr": 0.04351941398892446
},
"hendrycksTest-college_medicine": {
"acc": 0.2774566473988439,
"acc_stderr": 0.03414014007044036,
"acc_norm": 0.2774566473988439,
"acc_norm_stderr": 0.03414014007044036
},
"hendrycksTest-college_physics": {
"acc": 0.21568627450980393,
"acc_stderr": 0.04092563958237656,
"acc_norm": 0.21568627450980393,
"acc_norm_stderr": 0.04092563958237656
},
"hendrycksTest-computer_security": {
"acc": 0.49,
"acc_stderr": 0.05024183937956911,
"acc_norm": 0.49,
"acc_norm_stderr": 0.05024183937956911
},
"hendrycksTest-conceptual_physics": {
"acc": 0.3191489361702128,
"acc_stderr": 0.03047297336338004,
"acc_norm": 0.3191489361702128,
"acc_norm_stderr": 0.03047297336338004
},
"hendrycksTest-econometrics": {
"acc": 0.2894736842105263,
"acc_stderr": 0.042663394431593935,
"acc_norm": 0.2894736842105263,
"acc_norm_stderr": 0.042663394431593935
},
"hendrycksTest-electrical_engineering": {
"acc": 0.27586206896551724,
"acc_stderr": 0.037245636197746325,
"acc_norm": 0.27586206896551724,
"acc_norm_stderr": 0.037245636197746325
},
"hendrycksTest-elementary_mathematics": {
"acc": 0.2698412698412698,
"acc_stderr": 0.022860838309232072,
"acc_norm": 0.2698412698412698,
"acc_norm_stderr": 0.022860838309232072
},
"hendrycksTest-formal_logic": {
"acc": 0.31746031746031744,
"acc_stderr": 0.04163453031302859,
"acc_norm": 0.31746031746031744,
"acc_norm_stderr": 0.04163453031302859
},
"hendrycksTest-global_facts": {
"acc": 0.35,
"acc_stderr": 0.04793724854411018,
"acc_norm": 0.35,
"acc_norm_stderr": 0.04793724854411018
},
"hendrycksTest-high_school_biology": {
"acc": 0.25483870967741934,
"acc_stderr": 0.024790118459332208,
"acc_norm": 0.25483870967741934,
"acc_norm_stderr": 0.024790118459332208
},
"hendrycksTest-high_school_chemistry": {
"acc": 0.2512315270935961,
"acc_stderr": 0.030516530732694433,
"acc_norm": 0.2512315270935961,
"acc_norm_stderr": 0.030516530732694433
},
"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": 0.2787878787878788,
"acc_stderr": 0.03501438706296781,
"acc_norm": 0.2787878787878788,
"acc_norm_stderr": 0.03501438706296781
},
"hendrycksTest-high_school_geography": {
"acc": 0.24242424242424243,
"acc_stderr": 0.030532892233932026,
"acc_norm": 0.24242424242424243,
"acc_norm_stderr": 0.030532892233932026
},
"hendrycksTest-high_school_government_and_politics": {
"acc": 0.22797927461139897,
"acc_stderr": 0.03027690994517825,
"acc_norm": 0.22797927461139897,
"acc_norm_stderr": 0.03027690994517825
},
"hendrycksTest-high_school_macroeconomics": {
"acc": 0.2230769230769231,
"acc_stderr": 0.021107730127243995,
"acc_norm": 0.2230769230769231,
"acc_norm_stderr": 0.021107730127243995
},
"hendrycksTest-high_school_mathematics": {
"acc": 0.24814814814814815,
"acc_stderr": 0.0263357394040558,
"acc_norm": 0.24814814814814815,
"acc_norm_stderr": 0.0263357394040558
},
"hendrycksTest-high_school_microeconomics": {
"acc": 0.23949579831932774,
"acc_stderr": 0.02772206549336128,
"acc_norm": 0.23949579831932774,
"acc_norm_stderr": 0.02772206549336128
},
"hendrycksTest-high_school_physics": {
"acc": 0.2847682119205298,
"acc_stderr": 0.03684881521389023,
"acc_norm": 0.2847682119205298,
"acc_norm_stderr": 0.03684881521389023
},
"hendrycksTest-high_school_psychology": {
"acc": 0.28256880733944956,
"acc_stderr": 0.01930424349770715,
"acc_norm": 0.28256880733944956,
"acc_norm_stderr": 0.01930424349770715
},
"hendrycksTest-high_school_statistics": {
"acc": 0.26851851851851855,
"acc_stderr": 0.0302252261600124,
"acc_norm": 0.26851851851851855,
"acc_norm_stderr": 0.0302252261600124
},
"hendrycksTest-high_school_us_history": {
"acc": 0.22058823529411764,
"acc_stderr": 0.02910225438967409,
"acc_norm": 0.22058823529411764,
"acc_norm_stderr": 0.02910225438967409
},
"hendrycksTest-high_school_world_history": {
"acc": 0.2869198312236287,
"acc_stderr": 0.029443773022594693,
"acc_norm": 0.2869198312236287,
"acc_norm_stderr": 0.029443773022594693
},
"hendrycksTest-human_aging": {
"acc": 0.28699551569506726,
"acc_stderr": 0.030360379710291954,
"acc_norm": 0.28699551569506726,
"acc_norm_stderr": 0.030360379710291954
},
"hendrycksTest-human_sexuality": {
"acc": 0.2748091603053435,
"acc_stderr": 0.03915345408847835,
"acc_norm": 0.2748091603053435,
"acc_norm_stderr": 0.03915345408847835
},
"hendrycksTest-international_law": {
"acc": 0.3884297520661157,
"acc_stderr": 0.04449270350068382,
"acc_norm": 0.3884297520661157,
"acc_norm_stderr": 0.04449270350068382
},
"hendrycksTest-jurisprudence": {
"acc": 0.3425925925925926,
"acc_stderr": 0.045879047413018105,
"acc_norm": 0.3425925925925926,
"acc_norm_stderr": 0.045879047413018105
},
"hendrycksTest-logical_fallacies": {
"acc": 0.22699386503067484,
"acc_stderr": 0.032910995786157686,
"acc_norm": 0.22699386503067484,
"acc_norm_stderr": 0.032910995786157686
},
"hendrycksTest-machine_learning": {
"acc": 0.26785714285714285,
"acc_stderr": 0.04203277291467763,
"acc_norm": 0.26785714285714285,
"acc_norm_stderr": 0.04203277291467763
},
"hendrycksTest-management": {
"acc": 0.2621359223300971,
"acc_stderr": 0.04354631077260597,
"acc_norm": 0.2621359223300971,
"acc_norm_stderr": 0.04354631077260597
},
"hendrycksTest-marketing": {
"acc": 0.34615384615384615,
"acc_stderr": 0.0311669573672359,
"acc_norm": 0.34615384615384615,
"acc_norm_stderr": 0.0311669573672359
},
"hendrycksTest-medical_genetics": {
"acc": 0.27,
"acc_stderr": 0.044619604333847394,
"acc_norm": 0.27,
"acc_norm_stderr": 0.044619604333847394
},
"hendrycksTest-miscellaneous": {
"acc": 0.34227330779054915,
"acc_stderr": 0.016967031766413614,
"acc_norm": 0.34227330779054915,
"acc_norm_stderr": 0.016967031766413614
},
"hendrycksTest-moral_disputes": {
"acc": 0.30057803468208094,
"acc_stderr": 0.02468531686725781,
"acc_norm": 0.30057803468208094,
"acc_norm_stderr": 0.02468531686725781
},
"hendrycksTest-moral_scenarios": {
"acc": 0.2435754189944134,
"acc_stderr": 0.014355911964767864,
"acc_norm": 0.2435754189944134,
"acc_norm_stderr": 0.014355911964767864
},
"hendrycksTest-nutrition": {
"acc": 0.30392156862745096,
"acc_stderr": 0.02633661346904664,
"acc_norm": 0.30392156862745096,
"acc_norm_stderr": 0.02633661346904664
},
"hendrycksTest-philosophy": {
"acc": 0.36012861736334406,
"acc_stderr": 0.027264297599804012,
"acc_norm": 0.36012861736334406,
"acc_norm_stderr": 0.027264297599804012
},
"hendrycksTest-prehistory": {
"acc": 0.3117283950617284,
"acc_stderr": 0.02577311116963045,
"acc_norm": 0.3117283950617284,
"acc_norm_stderr": 0.02577311116963045
},
"hendrycksTest-professional_accounting": {
"acc": 0.2695035460992908,
"acc_stderr": 0.026469036818590638,
"acc_norm": 0.2695035460992908,
"acc_norm_stderr": 0.026469036818590638
},
"hendrycksTest-professional_law": {
"acc": 0.27640156453715775,
"acc_stderr": 0.011422153194553582,
"acc_norm": 0.27640156453715775,
"acc_norm_stderr": 0.011422153194553582
},
"hendrycksTest-professional_medicine": {
"acc": 0.20588235294117646,
"acc_stderr": 0.024562204314142314,
"acc_norm": 0.20588235294117646,
"acc_norm_stderr": 0.024562204314142314
},
"hendrycksTest-professional_psychology": {
"acc": 0.29411764705882354,
"acc_stderr": 0.018433427649401903,
"acc_norm": 0.29411764705882354,
"acc_norm_stderr": 0.018433427649401903
},
"hendrycksTest-public_relations": {
"acc": 0.37272727272727274,
"acc_stderr": 0.04631381319425463,
"acc_norm": 0.37272727272727274,
"acc_norm_stderr": 0.04631381319425463
},
"hendrycksTest-security_studies": {
"acc": 0.2530612244897959,
"acc_stderr": 0.027833023871399683,
"acc_norm": 0.2530612244897959,
"acc_norm_stderr": 0.027833023871399683
},
"hendrycksTest-sociology": {
"acc": 0.26865671641791045,
"acc_stderr": 0.03134328358208955,
"acc_norm": 0.26865671641791045,
"acc_norm_stderr": 0.03134328358208955
},
"hendrycksTest-us_foreign_policy": {
"acc": 0.35,
"acc_stderr": 0.047937248544110196,
"acc_norm": 0.35,
"acc_norm_stderr": 0.047937248544110196
},
"hendrycksTest-virology": {
"acc": 0.3614457831325301,
"acc_stderr": 0.037400593820293204,
"acc_norm": 0.3614457831325301,
"acc_norm_stderr": 0.037400593820293204
},
"hendrycksTest-world_religions": {
"acc": 0.3567251461988304,
"acc_stderr": 0.03674013002860954,
"acc_norm": 0.3567251461988304,
"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": "hf-causal",
"model_args": "pretrained=workdir_7b/ckpt_354",
"num_fewshot": 5,
"batch_size": "8",
"batch_sizes": [],
"device": null,
"no_cache": true,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}