{ "results": { "mmlu": { "acc,none": 0.6796040450078337, "acc_stderr,none": 0.0037536106989250334, "alias": "mmlu" }, "mmlu_humanities": { "acc,none": 0.6429330499468651, "acc_stderr,none": 0.006725053818853999, "alias": " - humanities" }, "mmlu_formal_logic": { "alias": " - formal_logic", "acc,none": 0.47619047619047616, "acc_stderr,none": 0.04467062628403273 }, "mmlu_high_school_european_history": { "alias": " - high_school_european_history", "acc,none": 0.7575757575757576, "acc_stderr,none": 0.03346409881055953 }, "mmlu_high_school_us_history": { "alias": " - high_school_us_history", "acc,none": 0.8431372549019608, "acc_stderr,none": 0.02552472232455334 }, "mmlu_high_school_world_history": { "alias": " - high_school_world_history", "acc,none": 0.8607594936708861, "acc_stderr,none": 0.022535526352692712 }, "mmlu_international_law": { "alias": " - international_law", "acc,none": 0.8181818181818182, "acc_stderr,none": 0.03520893951097653 }, "mmlu_jurisprudence": { "alias": " - jurisprudence", "acc,none": 0.7777777777777778, "acc_stderr,none": 0.0401910747255735 }, "mmlu_logical_fallacies": { "alias": " - logical_fallacies", "acc,none": 0.7914110429447853, "acc_stderr,none": 0.031921934489347256 }, "mmlu_moral_disputes": { "alias": " - moral_disputes", "acc,none": 0.7427745664739884, "acc_stderr,none": 0.02353292543104428 }, "mmlu_moral_scenarios": { "alias": " - moral_scenarios", "acc,none": 0.576536312849162, "acc_stderr,none": 0.016525425898773503 }, "mmlu_philosophy": { "alias": " - philosophy", "acc,none": 0.7138263665594855, "acc_stderr,none": 0.025670259242188936 }, "mmlu_prehistory": { "alias": " - prehistory", "acc,none": 0.7376543209876543, "acc_stderr,none": 0.02447722285613512 }, "mmlu_professional_law": { "alias": " - professional_law", "acc,none": 0.5052151238591917, "acc_stderr,none": 0.012769541449652547 }, "mmlu_world_religions": { "alias": " - world_religions", "acc,none": 0.8362573099415205, "acc_stderr,none": 0.028380919596145866 }, "mmlu_other": { "acc,none": 0.7421950434502735, "acc_stderr,none": 0.007551091352698539, "alias": " - other" }, "mmlu_business_ethics": { "alias": " - business_ethics", "acc,none": 0.68, "acc_stderr,none": 0.046882617226215034 }, "mmlu_clinical_knowledge": { "alias": " - clinical_knowledge", "acc,none": 0.7924528301886793, "acc_stderr,none": 0.02495991802891127 }, "mmlu_college_medicine": { "alias": " - college_medicine", "acc,none": 0.6878612716763006, "acc_stderr,none": 0.035331333893236574 }, "mmlu_global_facts": { "alias": " - global_facts", "acc,none": 0.41, "acc_stderr,none": 0.04943110704237102 }, "mmlu_human_aging": { "alias": " - human_aging", "acc,none": 0.7130044843049327, "acc_stderr,none": 0.030360379710291933 }, "mmlu_management": { "alias": " - management", "acc,none": 0.8155339805825242, "acc_stderr,none": 0.03840423627288276 }, "mmlu_marketing": { "alias": " - marketing", "acc,none": 0.8888888888888888, "acc_stderr,none": 0.020588491316092368 }, "mmlu_medical_genetics": { "alias": " - medical_genetics", "acc,none": 0.77, "acc_stderr,none": 0.04229525846816505 }, "mmlu_miscellaneous": { "alias": " - miscellaneous", "acc,none": 0.842911877394636, "acc_stderr,none": 0.013012459322650709 }, "mmlu_nutrition": { "alias": " - nutrition", "acc,none": 0.7516339869281046, "acc_stderr,none": 0.02473998135511359 }, "mmlu_professional_accounting": { "alias": " - professional_accounting", "acc,none": 0.5460992907801419, "acc_stderr,none": 0.02970045324729148 }, "mmlu_professional_medicine": { "alias": " - professional_medicine", "acc,none": 0.7757352941176471, "acc_stderr,none": 0.025336848563332348 }, "mmlu_virology": { "alias": " - virology", "acc,none": 0.5120481927710844, "acc_stderr,none": 0.03891364495835817 }, "mmlu_social_sciences": { "acc,none": 0.769580760480988, "acc_stderr,none": 0.007441632752136431, "alias": " - social sciences" }, "mmlu_econometrics": { "alias": " - econometrics", "acc,none": 0.5087719298245614, "acc_stderr,none": 0.04702880432049615 }, "mmlu_high_school_geography": { "alias": " - high_school_geography", "acc,none": 0.7929292929292929, "acc_stderr,none": 0.02886977846026705 }, "mmlu_high_school_government_and_politics": { "alias": " - high_school_government_and_politics", "acc,none": 0.8756476683937824, "acc_stderr,none": 0.023814477086593566 }, "mmlu_high_school_macroeconomics": { "alias": " - high_school_macroeconomics", "acc,none": 0.6794871794871795, "acc_stderr,none": 0.023661296393964273 }, "mmlu_high_school_microeconomics": { "alias": " - high_school_microeconomics", "acc,none": 0.7941176470588235, "acc_stderr,none": 0.02626502460827588 }, "mmlu_high_school_psychology": { "alias": " - high_school_psychology", "acc,none": 0.8623853211009175, "acc_stderr,none": 0.014770105878649395 }, "mmlu_human_sexuality": { "alias": " - human_sexuality", "acc,none": 0.8015267175572519, "acc_stderr,none": 0.0349814938546247 }, "mmlu_professional_psychology": { "alias": " - professional_psychology", "acc,none": 0.7156862745098039, "acc_stderr,none": 0.01824902441120766 }, "mmlu_public_relations": { "alias": " - public_relations", "acc,none": 0.6727272727272727, "acc_stderr,none": 0.04494290866252091 }, "mmlu_security_studies": { "alias": " - security_studies", "acc,none": 0.7551020408163265, "acc_stderr,none": 0.027529637440174927 }, "mmlu_sociology": { "alias": " - sociology", "acc,none": 0.8507462686567164, "acc_stderr,none": 0.025196929874827072 }, "mmlu_us_foreign_policy": { "alias": " - us_foreign_policy", "acc,none": 0.87, "acc_stderr,none": 0.03379976689896309 }, "mmlu_stem": { "acc,none": 0.5848398350777038, "acc_stderr,none": 0.008405009941949513, "alias": " - stem" }, "mmlu_abstract_algebra": { "alias": " - abstract_algebra", "acc,none": 0.34, "acc_stderr,none": 0.04760952285695235 }, "mmlu_anatomy": { "alias": " - anatomy", "acc,none": 0.6888888888888889, "acc_stderr,none": 0.03999262876617721 }, "mmlu_astronomy": { "alias": " - astronomy", "acc,none": 0.756578947368421, "acc_stderr,none": 0.034923496688842384 }, "mmlu_college_biology": { "alias": " - college_biology", "acc,none": 0.8194444444444444, "acc_stderr,none": 0.032166008088022675 }, "mmlu_college_chemistry": { "alias": " - college_chemistry", "acc,none": 0.46, "acc_stderr,none": 0.05009082659620333 }, "mmlu_college_computer_science": { "alias": " - college_computer_science", "acc,none": 0.57, "acc_stderr,none": 0.04975698519562427 }, "mmlu_college_mathematics": { "alias": " - college_mathematics", "acc,none": 0.35, "acc_stderr,none": 0.047937248544110196 }, "mmlu_college_physics": { "alias": " - college_physics", "acc,none": 0.4215686274509804, "acc_stderr,none": 0.04913595201274498 }, "mmlu_computer_security": { "alias": " - computer_security", "acc,none": 0.75, "acc_stderr,none": 0.04351941398892446 }, "mmlu_conceptual_physics": { "alias": " - conceptual_physics", "acc,none": 0.6, "acc_stderr,none": 0.03202563076101737 }, "mmlu_electrical_engineering": { "alias": " - electrical_engineering", "acc,none": 0.6551724137931034, "acc_stderr,none": 0.03960933549451208 }, "mmlu_elementary_mathematics": { "alias": " - elementary_mathematics", "acc,none": 0.49206349206349204, "acc_stderr,none": 0.025748065871673297 }, "mmlu_high_school_biology": { "alias": " - high_school_biology", "acc,none": 0.8096774193548387, "acc_stderr,none": 0.022331707611823078 }, "mmlu_high_school_chemistry": { "alias": " - high_school_chemistry", "acc,none": 0.645320197044335, "acc_stderr,none": 0.03366124489051449 }, "mmlu_high_school_computer_science": { "alias": " - high_school_computer_science", "acc,none": 0.74, "acc_stderr,none": 0.0440844002276808 }, "mmlu_high_school_mathematics": { "alias": " - high_school_mathematics", "acc,none": 0.4185185185185185, "acc_stderr,none": 0.03007801307502206 }, "mmlu_high_school_physics": { "alias": " - high_school_physics", "acc,none": 0.4503311258278146, "acc_stderr,none": 0.040622900186837764 }, "mmlu_high_school_statistics": { "alias": " - high_school_statistics", "acc,none": 0.5416666666666666, "acc_stderr,none": 0.03398110890294636 }, "mmlu_machine_learning": { "alias": " - machine_learning", "acc,none": 0.4642857142857143, "acc_stderr,none": 0.04733667890053757 } }, "groups": { "mmlu": { "acc,none": 0.6796040450078337, "acc_stderr,none": 0.0037536106989250334, "alias": "mmlu" }, "mmlu_humanities": { "acc,none": 0.6429330499468651, "acc_stderr,none": 0.006725053818853999, "alias": " - humanities" }, "mmlu_other": { "acc,none": 0.7421950434502735, "acc_stderr,none": 0.007551091352698539, "alias": " - other" }, "mmlu_social_sciences": { "acc,none": 0.769580760480988, "acc_stderr,none": 0.007441632752136431, "alias": " - social sciences" }, "mmlu_stem": { "acc,none": 0.5848398350777038, "acc_stderr,none": 0.008405009941949513, "alias": " - stem" } }, "group_subtasks": { "mmlu_humanities": [ "mmlu_high_school_world_history", "mmlu_high_school_european_history", "mmlu_prehistory", "mmlu_high_school_us_history", "mmlu_philosophy", "mmlu_jurisprudence", "mmlu_world_religions", "mmlu_logical_fallacies", "mmlu_moral_scenarios", "mmlu_international_law", "mmlu_moral_disputes", "mmlu_professional_law", "mmlu_formal_logic" ], "mmlu_social_sciences": [ "mmlu_high_school_geography", "mmlu_professional_psychology", "mmlu_high_school_government_and_politics", "mmlu_public_relations", "mmlu_human_sexuality", "mmlu_security_studies", "mmlu_econometrics", "mmlu_high_school_macroeconomics", "mmlu_high_school_microeconomics", "mmlu_us_foreign_policy", "mmlu_high_school_psychology", "mmlu_sociology" ], "mmlu_other": [ "mmlu_virology", "mmlu_human_aging", "mmlu_management", "mmlu_business_ethics", "mmlu_nutrition", "mmlu_marketing", "mmlu_medical_genetics", "mmlu_professional_medicine", "mmlu_college_medicine", "mmlu_miscellaneous", "mmlu_global_facts", "mmlu_clinical_knowledge", "mmlu_professional_accounting" ], "mmlu_stem": [ "mmlu_machine_learning", "mmlu_high_school_mathematics", "mmlu_high_school_chemistry", "mmlu_elementary_mathematics", "mmlu_high_school_computer_science", "mmlu_college_computer_science", "mmlu_college_mathematics", "mmlu_computer_security", "mmlu_electrical_engineering", "mmlu_anatomy", "mmlu_college_physics", "mmlu_high_school_physics", "mmlu_abstract_algebra", "mmlu_college_biology", "mmlu_high_school_statistics", "mmlu_college_chemistry", "mmlu_high_school_biology", "mmlu_astronomy", "mmlu_conceptual_physics" ], "mmlu": [ "mmlu_stem", "mmlu_other", "mmlu_social_sciences", "mmlu_humanities" ] }, "configs": { "mmlu_abstract_algebra": { "task": "mmlu_abstract_algebra", "task_alias": "abstract_algebra", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "abstract_algebra", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_anatomy": { "task": "mmlu_anatomy", "task_alias": "anatomy", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "anatomy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about anatomy.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_astronomy": { "task": "mmlu_astronomy", "task_alias": "astronomy", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "astronomy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about astronomy.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_business_ethics": { "task": "mmlu_business_ethics", "task_alias": "business_ethics", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "business_ethics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about business ethics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_clinical_knowledge": { "task": "mmlu_clinical_knowledge", "task_alias": "clinical_knowledge", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "clinical_knowledge", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_biology": { "task": "mmlu_college_biology", "task_alias": "college_biology", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_biology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college biology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_chemistry": { "task": "mmlu_college_chemistry", "task_alias": "college_chemistry", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_chemistry", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college chemistry.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_computer_science": { "task": "mmlu_college_computer_science", "task_alias": "college_computer_science", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_computer_science", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college computer science.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_mathematics": { "task": "mmlu_college_mathematics", "task_alias": "college_mathematics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_mathematics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college mathematics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_medicine": { "task": "mmlu_college_medicine", "task_alias": "college_medicine", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_medicine", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college medicine.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_college_physics": { "task": "mmlu_college_physics", "task_alias": "college_physics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_physics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about college physics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_computer_security": { "task": "mmlu_computer_security", "task_alias": "computer_security", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "computer_security", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about computer security.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_conceptual_physics": { "task": "mmlu_conceptual_physics", "task_alias": "conceptual_physics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "conceptual_physics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_econometrics": { "task": "mmlu_econometrics", "task_alias": "econometrics", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "econometrics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about econometrics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_electrical_engineering": { "task": "mmlu_electrical_engineering", "task_alias": "electrical_engineering", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "electrical_engineering", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_elementary_mathematics": { "task": "mmlu_elementary_mathematics", "task_alias": "elementary_mathematics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "elementary_mathematics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_formal_logic": { "task": "mmlu_formal_logic", "task_alias": "formal_logic", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "formal_logic", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about formal logic.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_global_facts": { "task": "mmlu_global_facts", "task_alias": "global_facts", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "global_facts", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about global facts.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_biology": { "task": "mmlu_high_school_biology", "task_alias": "high_school_biology", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_biology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school biology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_chemistry": { "task": "mmlu_high_school_chemistry", "task_alias": "high_school_chemistry", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_chemistry", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_computer_science": { "task": "mmlu_high_school_computer_science", "task_alias": "high_school_computer_science", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_computer_science", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school computer science.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_european_history": { "task": "mmlu_high_school_european_history", "task_alias": "high_school_european_history", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_european_history", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school european history.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_geography": { "task": "mmlu_high_school_geography", "task_alias": "high_school_geography", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_geography", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school geography.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_government_and_politics": { "task": "mmlu_high_school_government_and_politics", "task_alias": "high_school_government_and_politics", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_government_and_politics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_macroeconomics": { "task": "mmlu_high_school_macroeconomics", "task_alias": "high_school_macroeconomics", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_macroeconomics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_mathematics": { "task": "mmlu_high_school_mathematics", "task_alias": "high_school_mathematics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_mathematics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_microeconomics": { "task": "mmlu_high_school_microeconomics", "task_alias": "high_school_microeconomics", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_microeconomics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_physics": { "task": "mmlu_high_school_physics", "task_alias": "high_school_physics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_physics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school physics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_psychology": { "task": "mmlu_high_school_psychology", "task_alias": "high_school_psychology", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_psychology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school psychology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_statistics": { "task": "mmlu_high_school_statistics", "task_alias": "high_school_statistics", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_statistics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school statistics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_us_history": { "task": "mmlu_high_school_us_history", "task_alias": "high_school_us_history", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_us_history", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school us history.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_high_school_world_history": { "task": "mmlu_high_school_world_history", "task_alias": "high_school_world_history", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_world_history", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about high school world history.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_human_aging": { "task": "mmlu_human_aging", "task_alias": "human_aging", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "human_aging", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about human aging.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_human_sexuality": { "task": "mmlu_human_sexuality", "task_alias": "human_sexuality", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "human_sexuality", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about human sexuality.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_international_law": { "task": "mmlu_international_law", "task_alias": "international_law", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "international_law", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about international law.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_jurisprudence": { "task": "mmlu_jurisprudence", "task_alias": "jurisprudence", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "jurisprudence", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_logical_fallacies": { "task": "mmlu_logical_fallacies", "task_alias": "logical_fallacies", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "logical_fallacies", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_machine_learning": { "task": "mmlu_machine_learning", "task_alias": "machine_learning", "tag": "mmlu_stem_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "machine_learning", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about machine learning.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_management": { "task": "mmlu_management", "task_alias": "management", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "management", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about management.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_marketing": { "task": "mmlu_marketing", "task_alias": "marketing", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "marketing", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about marketing.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_medical_genetics": { "task": "mmlu_medical_genetics", "task_alias": "medical_genetics", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "medical_genetics", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about medical genetics.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_miscellaneous": { "task": "mmlu_miscellaneous", "task_alias": "miscellaneous", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "miscellaneous", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_moral_disputes": { "task": "mmlu_moral_disputes", "task_alias": "moral_disputes", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "moral_disputes", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about moral disputes.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_moral_scenarios": { "task": "mmlu_moral_scenarios", "task_alias": "moral_scenarios", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "moral_scenarios", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_nutrition": { "task": "mmlu_nutrition", "task_alias": "nutrition", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "nutrition", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about nutrition.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_philosophy": { "task": "mmlu_philosophy", "task_alias": "philosophy", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "philosophy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about philosophy.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_prehistory": { "task": "mmlu_prehistory", "task_alias": "prehistory", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "prehistory", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about prehistory.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_professional_accounting": { "task": "mmlu_professional_accounting", "task_alias": "professional_accounting", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_accounting", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about professional accounting.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_professional_law": { "task": "mmlu_professional_law", "task_alias": "professional_law", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_law", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about professional law.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_professional_medicine": { "task": "mmlu_professional_medicine", "task_alias": "professional_medicine", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_medicine", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about professional medicine.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_professional_psychology": { "task": "mmlu_professional_psychology", "task_alias": "professional_psychology", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_psychology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about professional psychology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_public_relations": { "task": "mmlu_public_relations", "task_alias": "public_relations", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "public_relations", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about public relations.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_security_studies": { "task": "mmlu_security_studies", "task_alias": "security_studies", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "security_studies", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about security studies.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_sociology": { "task": "mmlu_sociology", "task_alias": "sociology", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "sociology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about sociology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_us_foreign_policy": { "task": "mmlu_us_foreign_policy", "task_alias": "us_foreign_policy", "tag": "mmlu_social_sciences_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "us_foreign_policy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about us foreign policy.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_virology": { "task": "mmlu_virology", "task_alias": "virology", "tag": "mmlu_other_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "virology", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about virology.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "mmlu_world_religions": { "task": "mmlu_world_religions", "task_alias": "world_religions", "tag": "mmlu_humanities_tasks", "dataset_path": "hails/mmlu_no_train", "dataset_name": "world_religions", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "dev", "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:", "doc_to_target": "answer", "doc_to_choice": [ "A", "B", "C", "D" ], "description": "The following are multiple choice questions (with answers) about world religions.\n\n", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n" }, "num_fewshot": 0, "metric_list": [ { "metric": "acc", "aggregation": "mean", "higher_is_better": true } ], "output_type": "multiple_choice", "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } } }, "versions": { "mmlu": 2, "mmlu_abstract_algebra": 1.0, "mmlu_anatomy": 1.0, "mmlu_astronomy": 1.0, "mmlu_business_ethics": 1.0, "mmlu_clinical_knowledge": 1.0, "mmlu_college_biology": 1.0, "mmlu_college_chemistry": 1.0, "mmlu_college_computer_science": 1.0, "mmlu_college_mathematics": 1.0, "mmlu_college_medicine": 1.0, "mmlu_college_physics": 1.0, "mmlu_computer_security": 1.0, "mmlu_conceptual_physics": 1.0, "mmlu_econometrics": 1.0, "mmlu_electrical_engineering": 1.0, "mmlu_elementary_mathematics": 1.0, "mmlu_formal_logic": 1.0, "mmlu_global_facts": 1.0, "mmlu_high_school_biology": 1.0, "mmlu_high_school_chemistry": 1.0, "mmlu_high_school_computer_science": 1.0, "mmlu_high_school_european_history": 1.0, "mmlu_high_school_geography": 1.0, "mmlu_high_school_government_and_politics": 1.0, "mmlu_high_school_macroeconomics": 1.0, "mmlu_high_school_mathematics": 1.0, "mmlu_high_school_microeconomics": 1.0, "mmlu_high_school_physics": 1.0, "mmlu_high_school_psychology": 1.0, "mmlu_high_school_statistics": 1.0, "mmlu_high_school_us_history": 1.0, "mmlu_high_school_world_history": 1.0, "mmlu_human_aging": 1.0, "mmlu_human_sexuality": 1.0, "mmlu_humanities": 2, "mmlu_international_law": 1.0, "mmlu_jurisprudence": 1.0, "mmlu_logical_fallacies": 1.0, "mmlu_machine_learning": 1.0, "mmlu_management": 1.0, "mmlu_marketing": 1.0, "mmlu_medical_genetics": 1.0, "mmlu_miscellaneous": 1.0, "mmlu_moral_disputes": 1.0, "mmlu_moral_scenarios": 1.0, "mmlu_nutrition": 1.0, "mmlu_other": 2, "mmlu_philosophy": 1.0, "mmlu_prehistory": 1.0, "mmlu_professional_accounting": 1.0, "mmlu_professional_law": 1.0, "mmlu_professional_medicine": 1.0, "mmlu_professional_psychology": 1.0, "mmlu_public_relations": 1.0, "mmlu_security_studies": 1.0, "mmlu_social_sciences": 2, "mmlu_sociology": 1.0, "mmlu_stem": 2, "mmlu_us_foreign_policy": 1.0, "mmlu_virology": 1.0, "mmlu_world_religions": 1.0 }, "n-shot": { "mmlu_abstract_algebra": 0, "mmlu_anatomy": 0, "mmlu_astronomy": 0, "mmlu_business_ethics": 0, "mmlu_clinical_knowledge": 0, "mmlu_college_biology": 0, "mmlu_college_chemistry": 0, "mmlu_college_computer_science": 0, "mmlu_college_mathematics": 0, "mmlu_college_medicine": 0, "mmlu_college_physics": 0, "mmlu_computer_security": 0, "mmlu_conceptual_physics": 0, "mmlu_econometrics": 0, "mmlu_electrical_engineering": 0, "mmlu_elementary_mathematics": 0, "mmlu_formal_logic": 0, "mmlu_global_facts": 0, "mmlu_high_school_biology": 0, "mmlu_high_school_chemistry": 0, "mmlu_high_school_computer_science": 0, "mmlu_high_school_european_history": 0, "mmlu_high_school_geography": 0, "mmlu_high_school_government_and_politics": 0, "mmlu_high_school_macroeconomics": 0, "mmlu_high_school_mathematics": 0, "mmlu_high_school_microeconomics": 0, "mmlu_high_school_physics": 0, "mmlu_high_school_psychology": 0, "mmlu_high_school_statistics": 0, "mmlu_high_school_us_history": 0, "mmlu_high_school_world_history": 0, "mmlu_human_aging": 0, "mmlu_human_sexuality": 0, "mmlu_international_law": 0, "mmlu_jurisprudence": 0, "mmlu_logical_fallacies": 0, "mmlu_machine_learning": 0, "mmlu_management": 0, "mmlu_marketing": 0, "mmlu_medical_genetics": 0, "mmlu_miscellaneous": 0, "mmlu_moral_disputes": 0, "mmlu_moral_scenarios": 0, "mmlu_nutrition": 0, "mmlu_philosophy": 0, "mmlu_prehistory": 0, "mmlu_professional_accounting": 0, "mmlu_professional_law": 0, "mmlu_professional_medicine": 0, "mmlu_professional_psychology": 0, "mmlu_public_relations": 0, "mmlu_security_studies": 0, "mmlu_sociology": 0, "mmlu_us_foreign_policy": 0, "mmlu_virology": 0, "mmlu_world_religions": 0 }, "higher_is_better": { "mmlu": { "acc": true }, "mmlu_abstract_algebra": { "acc": true }, "mmlu_anatomy": { "acc": true }, "mmlu_astronomy": { "acc": true }, "mmlu_business_ethics": { "acc": true }, "mmlu_clinical_knowledge": { "acc": true }, "mmlu_college_biology": { "acc": true }, "mmlu_college_chemistry": { "acc": true }, "mmlu_college_computer_science": { "acc": true }, "mmlu_college_mathematics": { "acc": true }, "mmlu_college_medicine": { "acc": true }, "mmlu_college_physics": { "acc": true }, "mmlu_computer_security": { "acc": true }, "mmlu_conceptual_physics": { "acc": true }, "mmlu_econometrics": { "acc": true }, "mmlu_electrical_engineering": { "acc": true }, "mmlu_elementary_mathematics": { "acc": true }, "mmlu_formal_logic": { "acc": true }, "mmlu_global_facts": { "acc": true }, "mmlu_high_school_biology": { "acc": true }, "mmlu_high_school_chemistry": { "acc": true }, "mmlu_high_school_computer_science": { "acc": true }, "mmlu_high_school_european_history": { "acc": true }, "mmlu_high_school_geography": { "acc": true }, "mmlu_high_school_government_and_politics": { "acc": true }, "mmlu_high_school_macroeconomics": { "acc": true }, "mmlu_high_school_mathematics": { "acc": true }, "mmlu_high_school_microeconomics": { "acc": true }, "mmlu_high_school_physics": { "acc": true }, "mmlu_high_school_psychology": { "acc": true }, "mmlu_high_school_statistics": { "acc": true }, "mmlu_high_school_us_history": { "acc": true }, "mmlu_high_school_world_history": { "acc": true }, "mmlu_human_aging": { "acc": true }, "mmlu_human_sexuality": { "acc": true }, "mmlu_humanities": { "acc": true }, "mmlu_international_law": { "acc": true }, "mmlu_jurisprudence": { "acc": true }, "mmlu_logical_fallacies": { "acc": true }, "mmlu_machine_learning": { "acc": true }, "mmlu_management": { "acc": true }, "mmlu_marketing": { "acc": true }, "mmlu_medical_genetics": { "acc": true }, "mmlu_miscellaneous": { "acc": true }, "mmlu_moral_disputes": { "acc": true }, "mmlu_moral_scenarios": { "acc": true }, "mmlu_nutrition": { "acc": true }, "mmlu_other": { "acc": true }, "mmlu_philosophy": { "acc": true }, "mmlu_prehistory": { "acc": true }, "mmlu_professional_accounting": { "acc": true }, "mmlu_professional_law": { "acc": true }, "mmlu_professional_medicine": { "acc": true }, "mmlu_professional_psychology": { "acc": true }, "mmlu_public_relations": { "acc": true }, "mmlu_security_studies": { "acc": true }, "mmlu_social_sciences": { "acc": true }, "mmlu_sociology": { "acc": true }, "mmlu_stem": { "acc": true }, "mmlu_us_foreign_policy": { "acc": true }, "mmlu_virology": { "acc": true }, "mmlu_world_religions": { "acc": true } }, "n-samples": { "mmlu_machine_learning": { "original": 112, "effective": 112 }, "mmlu_high_school_mathematics": { "original": 270, "effective": 270 }, "mmlu_high_school_chemistry": { "original": 203, "effective": 203 }, "mmlu_elementary_mathematics": { "original": 378, "effective": 378 }, "mmlu_high_school_computer_science": { "original": 100, "effective": 100 }, "mmlu_college_computer_science": { "original": 100, "effective": 100 }, "mmlu_college_mathematics": { "original": 100, "effective": 100 }, "mmlu_computer_security": { "original": 100, "effective": 100 }, "mmlu_electrical_engineering": { "original": 145, "effective": 145 }, "mmlu_anatomy": { "original": 135, "effective": 135 }, "mmlu_college_physics": { "original": 102, "effective": 102 }, "mmlu_high_school_physics": { "original": 151, "effective": 151 }, "mmlu_abstract_algebra": { "original": 100, "effective": 100 }, "mmlu_college_biology": { "original": 144, "effective": 144 }, "mmlu_high_school_statistics": { "original": 216, "effective": 216 }, "mmlu_college_chemistry": { "original": 100, "effective": 100 }, "mmlu_high_school_biology": { "original": 310, "effective": 310 }, "mmlu_astronomy": { "original": 152, "effective": 152 }, "mmlu_conceptual_physics": { "original": 235, "effective": 235 }, "mmlu_virology": { "original": 166, "effective": 166 }, "mmlu_human_aging": { "original": 223, "effective": 223 }, "mmlu_management": { "original": 103, "effective": 103 }, "mmlu_business_ethics": { "original": 100, "effective": 100 }, "mmlu_nutrition": { "original": 306, "effective": 306 }, "mmlu_marketing": { "original": 234, "effective": 234 }, "mmlu_medical_genetics": { "original": 100, "effective": 100 }, "mmlu_professional_medicine": { "original": 272, "effective": 272 }, "mmlu_college_medicine": { "original": 173, "effective": 173 }, "mmlu_miscellaneous": { "original": 783, "effective": 783 }, "mmlu_global_facts": { "original": 100, "effective": 100 }, "mmlu_clinical_knowledge": { "original": 265, "effective": 265 }, "mmlu_professional_accounting": { "original": 282, "effective": 282 }, "mmlu_high_school_geography": { "original": 198, "effective": 198 }, "mmlu_professional_psychology": { "original": 612, "effective": 612 }, "mmlu_high_school_government_and_politics": { "original": 193, "effective": 193 }, "mmlu_public_relations": { "original": 110, "effective": 110 }, "mmlu_human_sexuality": { "original": 131, "effective": 131 }, "mmlu_security_studies": { "original": 245, "effective": 245 }, "mmlu_econometrics": { "original": 114, "effective": 114 }, "mmlu_high_school_macroeconomics": { "original": 390, "effective": 390 }, "mmlu_high_school_microeconomics": { "original": 238, "effective": 238 }, "mmlu_us_foreign_policy": { "original": 100, "effective": 100 }, "mmlu_high_school_psychology": { "original": 545, "effective": 545 }, "mmlu_sociology": { "original": 201, "effective": 201 }, "mmlu_high_school_world_history": { "original": 237, "effective": 237 }, "mmlu_high_school_european_history": { "original": 165, "effective": 165 }, "mmlu_prehistory": { "original": 324, "effective": 324 }, "mmlu_high_school_us_history": { "original": 204, "effective": 204 }, "mmlu_philosophy": { "original": 311, "effective": 311 }, "mmlu_jurisprudence": { "original": 108, "effective": 108 }, "mmlu_world_religions": { "original": 171, "effective": 171 }, "mmlu_logical_fallacies": { "original": 163, "effective": 163 }, "mmlu_moral_scenarios": { "original": 895, "effective": 895 }, "mmlu_international_law": { "original": 121, "effective": 121 }, "mmlu_moral_disputes": { "original": 346, "effective": 346 }, "mmlu_professional_law": { "original": 1534, "effective": 1534 }, "mmlu_formal_logic": { "original": 126, "effective": 126 } }, "config": { "model": "hf", "model_args": "pretrained=meta-llama/Meta-Llama-3.1-8B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=False", "model_num_parameters": 8030261248, "model_dtype": "torch.bfloat16", "model_revision": "main", "model_sha": "0e9e39f249a16976918f6564b8830bc894c89659", "batch_size": "auto", "batch_sizes": [ 64 ], "device": null, "use_cache": null, "limit": null, "bootstrap_iters": 100000, "gen_kwargs": null, "random_seed": 0, "numpy_seed": 1234, "torch_seed": 1234, "fewshot_seed": 1234 }, "git_hash": "788a3672", "date": 1737779632.761471, "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 48\nOn-line CPU(s) list: 0-47\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V13 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 1\nStepping: 1\nBogoMIPS: 4890.87\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 1.5 MiB (48 instances)\nL1i cache: 1.5 MiB (48 instances)\nL2 cache: 24 MiB (48 instances)\nL3 cache: 192 MiB (6 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Vulnerable\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect", "transformers_version": "4.48.1", "upper_git_hash": "086919bd66f4e15fdcd4b792a7b27a698c1ba091", "tokenizer_pad_token": [ "<|eot_id|>", "128009" ], "tokenizer_eos_token": [ "<|eot_id|>", "128009" ], "tokenizer_bos_token": [ "<|begin_of_text|>", "128000" ], "eot_token_id": 128009, "max_length": 131072, "task_hashes": {}, "model_source": "hf", "model_name": "meta-llama/Meta-Llama-3.1-8B-Instruct", "model_name_sanitized": "meta-llama__Meta-Llama-3.1-8B-Instruct", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 26713.857944153, "end_time": 26902.892605552, "total_evaluation_time_seconds": "189.03466139900047" }