{ "results": { "mmlu": { "acc,none": 0.6522575131747614, "acc_stderr,none": 0.00375442237713615, "alias": "mmlu" }, "mmlu_humanities": { "acc,none": 0.5995749202975558, "acc_stderr,none": 0.006560646191394197, "alias": " - humanities" }, "mmlu_formal_logic": { "alias": " - formal_logic", "acc,none": 0.4523809523809524, "acc_stderr,none": 0.044518079590553275 }, "mmlu_high_school_european_history": { "alias": " - high_school_european_history", "acc,none": 0.8424242424242424, "acc_stderr,none": 0.028450388805284332 }, "mmlu_high_school_us_history": { "alias": " - high_school_us_history", "acc,none": 0.8774509803921569, "acc_stderr,none": 0.023015389732458258 }, "mmlu_high_school_world_history": { "alias": " - high_school_world_history", "acc,none": 0.8649789029535865, "acc_stderr,none": 0.022245776632003694 }, "mmlu_international_law": { "alias": " - international_law", "acc,none": 0.7768595041322314, "acc_stderr,none": 0.03800754475228733 }, "mmlu_jurisprudence": { "alias": " - jurisprudence", "acc,none": 0.7777777777777778, "acc_stderr,none": 0.0401910747255735 }, "mmlu_logical_fallacies": { "alias": " - logical_fallacies", "acc,none": 0.7791411042944786, "acc_stderr,none": 0.032591773927421776 }, "mmlu_moral_disputes": { "alias": " - moral_disputes", "acc,none": 0.7283236994219653, "acc_stderr,none": 0.023948512905468348 }, "mmlu_moral_scenarios": { "alias": " - moral_scenarios", "acc,none": 0.29608938547486036, "acc_stderr,none": 0.015268677317602281 }, "mmlu_philosophy": { "alias": " - philosophy", "acc,none": 0.752411575562701, "acc_stderr,none": 0.024513879973621967 }, "mmlu_prehistory": { "alias": " - prehistory", "acc,none": 0.7592592592592593, "acc_stderr,none": 0.023788583551658537 }, "mmlu_professional_law": { "alias": " - professional_law", "acc,none": 0.5202086049543677, "acc_stderr,none": 0.012759801427767559 }, "mmlu_world_religions": { "alias": " - world_religions", "acc,none": 0.8245614035087719, "acc_stderr,none": 0.02917088550072767 }, "mmlu_other": { "acc,none": 0.7100096556163502, "acc_stderr,none": 0.007844213155132828, "alias": " - other" }, "mmlu_business_ethics": { "alias": " - business_ethics", "acc,none": 0.71, "acc_stderr,none": 0.045604802157206845 }, "mmlu_clinical_knowledge": { "alias": " - clinical_knowledge", "acc,none": 0.7169811320754716, "acc_stderr,none": 0.027724236492700918 }, "mmlu_college_medicine": { "alias": " - college_medicine", "acc,none": 0.630057803468208, "acc_stderr,none": 0.0368122963339432 }, "mmlu_global_facts": { "alias": " - global_facts", "acc,none": 0.44, "acc_stderr,none": 0.04988876515698589 }, "mmlu_human_aging": { "alias": " - human_aging", "acc,none": 0.7623318385650224, "acc_stderr,none": 0.02856807946471428 }, "mmlu_management": { "alias": " - management", "acc,none": 0.8058252427184466, "acc_stderr,none": 0.03916667762822582 }, "mmlu_marketing": { "alias": " - marketing", "acc,none": 0.8846153846153846, "acc_stderr,none": 0.02093019318517933 }, "mmlu_medical_genetics": { "alias": " - medical_genetics", "acc,none": 0.72, "acc_stderr,none": 0.04512608598542127 }, "mmlu_miscellaneous": { "alias": " - miscellaneous", "acc,none": 0.8109833971902938, "acc_stderr,none": 0.014000791294406999 }, "mmlu_nutrition": { "alias": " - nutrition", "acc,none": 0.7483660130718954, "acc_stderr,none": 0.024848018263875192 }, "mmlu_professional_accounting": { "alias": " - professional_accounting", "acc,none": 0.4787234042553192, "acc_stderr,none": 0.029800481645628693 }, "mmlu_professional_medicine": { "alias": " - professional_medicine", "acc,none": 0.6470588235294118, "acc_stderr,none": 0.029029422815681407 }, "mmlu_virology": { "alias": " - virology", "acc,none": 0.5120481927710844, "acc_stderr,none": 0.03891364495835817 }, "mmlu_social_sciences": { "acc,none": 0.7676308092297692, "acc_stderr,none": 0.00740933282907595, "alias": " - social sciences" }, "mmlu_econometrics": { "alias": " - econometrics", "acc,none": 0.43859649122807015, "acc_stderr,none": 0.04668000738510455 }, "mmlu_high_school_geography": { "alias": " - high_school_geography", "acc,none": 0.8434343434343434, "acc_stderr,none": 0.025890520358141454 }, "mmlu_high_school_government_and_politics": { "alias": " - high_school_government_and_politics", "acc,none": 0.917098445595855, "acc_stderr,none": 0.01989934131572178 }, "mmlu_high_school_macroeconomics": { "alias": " - high_school_macroeconomics", "acc,none": 0.6666666666666666, "acc_stderr,none": 0.023901157979402534 }, "mmlu_high_school_microeconomics": { "alias": " - high_school_microeconomics", "acc,none": 0.7563025210084033, "acc_stderr,none": 0.02788682807838058 }, "mmlu_high_school_psychology": { "alias": " - high_school_psychology", "acc,none": 0.8550458715596331, "acc_stderr,none": 0.015094215699700462 }, "mmlu_human_sexuality": { "alias": " - human_sexuality", "acc,none": 0.7786259541984732, "acc_stderr,none": 0.036412970813137276 }, "mmlu_professional_psychology": { "alias": " - professional_psychology", "acc,none": 0.7140522875816994, "acc_stderr,none": 0.018280485072954683 }, "mmlu_public_relations": { "alias": " - public_relations", "acc,none": 0.7545454545454545, "acc_stderr,none": 0.041220665028782855 }, "mmlu_security_studies": { "alias": " - security_studies", "acc,none": 0.7428571428571429, "acc_stderr,none": 0.027979823538744546 }, "mmlu_sociology": { "alias": " - sociology", "acc,none": 0.8208955223880597, "acc_stderr,none": 0.027113286753111837 }, "mmlu_us_foreign_policy": { "alias": " - us_foreign_policy", "acc,none": 0.93, "acc_stderr,none": 0.025643239997624294 }, "mmlu_stem": { "acc,none": 0.5613701236917221, "acc_stderr,none": 0.008468341117645424, "alias": " - stem" }, "mmlu_abstract_algebra": { "alias": " - abstract_algebra", "acc,none": 0.32, "acc_stderr,none": 0.046882617226215034 }, "mmlu_anatomy": { "alias": " - anatomy", "acc,none": 0.5555555555555556, "acc_stderr,none": 0.04292596718256981 }, "mmlu_astronomy": { "alias": " - astronomy", "acc,none": 0.75, "acc_stderr,none": 0.03523807393012047 }, "mmlu_college_biology": { "alias": " - college_biology", "acc,none": 0.75, "acc_stderr,none": 0.03621034121889507 }, "mmlu_college_chemistry": { "alias": " - college_chemistry", "acc,none": 0.5, "acc_stderr,none": 0.050251890762960605 }, "mmlu_college_computer_science": { "alias": " - college_computer_science", "acc,none": 0.57, "acc_stderr,none": 0.049756985195624284 }, "mmlu_college_mathematics": { "alias": " - college_mathematics", "acc,none": 0.36, "acc_stderr,none": 0.048241815132442176 }, "mmlu_college_physics": { "alias": " - college_physics", "acc,none": 0.46078431372549017, "acc_stderr,none": 0.04959859966384181 }, "mmlu_computer_security": { "alias": " - computer_security", "acc,none": 0.75, "acc_stderr,none": 0.04351941398892446 }, "mmlu_conceptual_physics": { "alias": " - conceptual_physics", "acc,none": 0.5617021276595745, "acc_stderr,none": 0.03243618636108102 }, "mmlu_electrical_engineering": { "alias": " - electrical_engineering", "acc,none": 0.6413793103448275, "acc_stderr,none": 0.03996629574876719 }, "mmlu_elementary_mathematics": { "alias": " - elementary_mathematics", "acc,none": 0.4603174603174603, "acc_stderr,none": 0.025670080636909193 }, "mmlu_high_school_biology": { "alias": " - high_school_biology", "acc,none": 0.8129032258064516, "acc_stderr,none": 0.02218571009225225 }, "mmlu_high_school_chemistry": { "alias": " - high_school_chemistry", "acc,none": 0.4876847290640394, "acc_stderr,none": 0.035169204442208966 }, "mmlu_high_school_computer_science": { "alias": " - high_school_computer_science", "acc,none": 0.65, "acc_stderr,none": 0.0479372485441102 }, "mmlu_high_school_mathematics": { "alias": " - high_school_mathematics", "acc,none": 0.37037037037037035, "acc_stderr,none": 0.02944316932303154 }, "mmlu_high_school_physics": { "alias": " - high_school_physics", "acc,none": 0.3841059602649007, "acc_stderr,none": 0.03971301814719198 }, "mmlu_high_school_statistics": { "alias": " - high_school_statistics", "acc,none": 0.6435185185185185, "acc_stderr,none": 0.032664783315272714 }, "mmlu_machine_learning": { "alias": " - machine_learning", "acc,none": 0.5714285714285714, "acc_stderr,none": 0.04697113923010212 } }, "groups": { "mmlu": { "acc,none": 0.6522575131747614, "acc_stderr,none": 0.00375442237713615, "alias": "mmlu" }, "mmlu_humanities": { "acc,none": 0.5995749202975558, "acc_stderr,none": 0.006560646191394197, "alias": " - humanities" }, "mmlu_other": { "acc,none": 0.7100096556163502, "acc_stderr,none": 0.007844213155132828, "alias": " - other" }, "mmlu_social_sciences": { "acc,none": 0.7676308092297692, "acc_stderr,none": 0.00740933282907595, "alias": " - social sciences" }, "mmlu_stem": { "acc,none": 0.5613701236917221, "acc_stderr,none": 0.008468341117645424, "alias": " - stem" } }, "group_subtasks": { "mmlu_humanities": [ "mmlu_high_school_world_history", "mmlu_high_school_european_history", "mmlu_high_school_us_history", "mmlu_logical_fallacies", "mmlu_moral_scenarios", "mmlu_formal_logic", "mmlu_moral_disputes", "mmlu_prehistory", "mmlu_world_religions", "mmlu_philosophy", "mmlu_jurisprudence", "mmlu_international_law", "mmlu_professional_law" ], "mmlu_social_sciences": [ "mmlu_high_school_government_and_politics", "mmlu_human_sexuality", "mmlu_high_school_psychology", "mmlu_sociology", "mmlu_high_school_macroeconomics", "mmlu_us_foreign_policy", "mmlu_high_school_geography", "mmlu_public_relations", "mmlu_professional_psychology", "mmlu_high_school_microeconomics", "mmlu_security_studies", "mmlu_econometrics" ], "mmlu_other": [ "mmlu_human_aging", "mmlu_professional_medicine", "mmlu_clinical_knowledge", "mmlu_nutrition", "mmlu_marketing", "mmlu_business_ethics", "mmlu_global_facts", "mmlu_miscellaneous", "mmlu_management", "mmlu_college_medicine", "mmlu_medical_genetics", "mmlu_professional_accounting", "mmlu_virology" ], "mmlu_stem": [ "mmlu_high_school_statistics", "mmlu_astronomy", "mmlu_college_chemistry", "mmlu_college_physics", "mmlu_college_biology", "mmlu_high_school_mathematics", "mmlu_machine_learning", "mmlu_abstract_algebra", "mmlu_anatomy", "mmlu_elementary_mathematics", "mmlu_college_computer_science", "mmlu_high_school_chemistry", "mmlu_high_school_biology", "mmlu_computer_security", "mmlu_college_mathematics", "mmlu_high_school_computer_science", "mmlu_electrical_engineering", "mmlu_conceptual_physics", "mmlu_high_school_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_high_school_statistics": { "original": 216, "effective": 216 }, "mmlu_astronomy": { "original": 152, "effective": 152 }, "mmlu_college_chemistry": { "original": 100, "effective": 100 }, "mmlu_college_physics": { "original": 102, "effective": 102 }, "mmlu_college_biology": { "original": 144, "effective": 144 }, "mmlu_high_school_mathematics": { "original": 270, "effective": 270 }, "mmlu_machine_learning": { "original": 112, "effective": 112 }, "mmlu_abstract_algebra": { "original": 100, "effective": 100 }, "mmlu_anatomy": { "original": 135, "effective": 135 }, "mmlu_elementary_mathematics": { "original": 378, "effective": 378 }, "mmlu_college_computer_science": { "original": 100, "effective": 100 }, "mmlu_high_school_chemistry": { "original": 203, "effective": 203 }, "mmlu_high_school_biology": { "original": 310, "effective": 310 }, "mmlu_computer_security": { "original": 100, "effective": 100 }, "mmlu_college_mathematics": { "original": 100, "effective": 100 }, "mmlu_high_school_computer_science": { "original": 100, "effective": 100 }, "mmlu_electrical_engineering": { "original": 145, "effective": 145 }, "mmlu_conceptual_physics": { "original": 235, "effective": 235 }, "mmlu_high_school_physics": { "original": 151, "effective": 151 }, "mmlu_human_aging": { "original": 223, "effective": 223 }, "mmlu_professional_medicine": { "original": 272, "effective": 272 }, "mmlu_clinical_knowledge": { "original": 265, "effective": 265 }, "mmlu_nutrition": { "original": 306, "effective": 306 }, "mmlu_marketing": { "original": 234, "effective": 234 }, "mmlu_business_ethics": { "original": 100, "effective": 100 }, "mmlu_global_facts": { "original": 100, "effective": 100 }, "mmlu_miscellaneous": { "original": 783, "effective": 783 }, "mmlu_management": { "original": 103, "effective": 103 }, "mmlu_college_medicine": { "original": 173, "effective": 173 }, "mmlu_medical_genetics": { "original": 100, "effective": 100 }, "mmlu_professional_accounting": { "original": 282, "effective": 282 }, "mmlu_virology": { "original": 166, "effective": 166 }, "mmlu_high_school_government_and_politics": { "original": 193, "effective": 193 }, "mmlu_human_sexuality": { "original": 131, "effective": 131 }, "mmlu_high_school_psychology": { "original": 545, "effective": 545 }, "mmlu_sociology": { "original": 201, "effective": 201 }, "mmlu_high_school_macroeconomics": { "original": 390, "effective": 390 }, "mmlu_us_foreign_policy": { "original": 100, "effective": 100 }, "mmlu_high_school_geography": { "original": 198, "effective": 198 }, "mmlu_public_relations": { "original": 110, "effective": 110 }, "mmlu_professional_psychology": { "original": 612, "effective": 612 }, "mmlu_high_school_microeconomics": { "original": 238, "effective": 238 }, "mmlu_security_studies": { "original": 245, "effective": 245 }, "mmlu_econometrics": { "original": 114, "effective": 114 }, "mmlu_high_school_world_history": { "original": 237, "effective": 237 }, "mmlu_high_school_european_history": { "original": 165, "effective": 165 }, "mmlu_high_school_us_history": { "original": 204, "effective": 204 }, "mmlu_logical_fallacies": { "original": 163, "effective": 163 }, "mmlu_moral_scenarios": { "original": 895, "effective": 895 }, "mmlu_formal_logic": { "original": 126, "effective": 126 }, "mmlu_moral_disputes": { "original": 346, "effective": 346 }, "mmlu_prehistory": { "original": 324, "effective": 324 }, "mmlu_world_religions": { "original": 171, "effective": 171 }, "mmlu_philosophy": { "original": 311, "effective": 311 }, "mmlu_jurisprudence": { "original": 108, "effective": 108 }, "mmlu_international_law": { "original": 121, "effective": 121 }, "mmlu_professional_law": { "original": 1534, "effective": 1534 } }, "config": { "model": "hf", "model_args": "pretrained=inceptionai/jais-adapted-70b-chat,trust_remote_code=True,cache_dir=/tmp,parallelize=True", "model_num_parameters": 69500936192, "model_dtype": "torch.float32", "model_revision": "main", "model_sha": "07c93d6799cba82e240633e5fc9bb4cceea6feb2", "batch_size": "auto", "batch_sizes": [ 32 ], "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": "150ae04f", "date": 1737632572.1049643, "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-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\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): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.88\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 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 ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\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: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\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": null, "tokenizer_pad_token": [ "", "0" ], "tokenizer_eos_token": [ "", "2" ], "tokenizer_bos_token": [ "", "1" ], "eot_token_id": 2, "max_length": 4096, "task_hashes": { "mmlu_high_school_statistics": "d46af02553938b20e9bce032a6ad424a0d56ae6e7784d0a351a96185695653f0", "mmlu_astronomy": "c9eca6773bb6f58214e51f833bfd88e5eafcaa0c05d0a4c2ee3e9bbed1272002", "mmlu_college_chemistry": "9d6d9332909abd7956faabfd895b7bd46a1085f65f31678e8f3535fee315a29a", "mmlu_college_physics": "3f3da5b2a15744fd5445d372a816c3b07433b0ea50cb9e7fc8e08a8b2b2b962b", "mmlu_college_biology": "d983837a4ac4327e74ff7f131eda1f0c23f6c9f2a1088e3a5162c6ede31605d5", "mmlu_high_school_mathematics": "fcb250f2c0a888667054bdaa209b5c2b677ecc9c1ac81fa8b8dce87a05dbc3d7", "mmlu_machine_learning": "4aa26a0049db413da3860533cc38acdf747bafd4849f6f6fc9f58028bb8b4cc6", "mmlu_abstract_algebra": "019c53bb7725c435b6977919f6e4a0043f6045691070942190fe4e0257b6e1e4", "mmlu_anatomy": "8a394ba6aa4d3366637e72da67c7d4c0286d47cb371a4f4a9814259be8bbe3ad", "mmlu_elementary_mathematics": "5f96932b45fc8d0ea0e09c979e7a0290505fb53fdb647624ad00ca162a2a7c50", "mmlu_college_computer_science": "44cc706099add4f2fa3d3903e33447378c38401a9b22e738008aef4db99ca7ae", "mmlu_high_school_chemistry": "1c7e3e5bffefd467481de9fb6425ec50eca053f9fce3b25af745ff886195176b", "mmlu_high_school_biology": "18ee3f74ce477d1ee3492951cfae846b1903dfcc4d107227ffaa6e305681a20f", "mmlu_computer_security": "9d94057a3894877d08645c17c769a104d28a2ed4249de8865d23d46953b15545", "mmlu_college_mathematics": "f1a2766207148367dedfa3e2961fc69de59078cfbc9631210b38068c0df8bbd7", "mmlu_high_school_computer_science": "34a7f3d2bbe6a0dc39d03973d87f9053076ccfbd7ea7ab40dca7073b68640db7", "mmlu_electrical_engineering": "fd6ef46bf380068043ad0568d1987c5485397a06d582f3f546bf2bea6cc02f3a", "mmlu_conceptual_physics": "ab3e1ecbb255ddc5c9ce70494d102bda7e259eb20596633235a42ca3d635239b", "mmlu_high_school_physics": "59513856cfc584e2815f43814216c8143f9c8866599ed8aaf7d53eec6ce308e9", "mmlu_human_aging": "2127e79731bae760ca6ff04ca6f2217d030a612d04a868032f4f6d8b42293550", "mmlu_professional_medicine": "b1c4eea40bd1d93e49c50cadd35db8bbb96392c40d208ae1ffd6e72c306d757a", "mmlu_clinical_knowledge": "839bf7b05724190f7277a957e8b2183a7b4dc74ab9ca72063d10872092a1ea7a", "mmlu_nutrition": "5a8f9ce8f1f4e9179460896281757c2f3e0c127c150608a5801d41101f6e8df1", "mmlu_marketing": "5ae8fb39ae90c5cd69adbffe8a62ebd10813d8da0d61fcd05cf143c65cee0303", "mmlu_business_ethics": "0115853241ce686fdf365cd34614a8b07067e96c385e2820e77c6820f1e1ea0b", "mmlu_global_facts": "217258f063f285ebf53d6ade8753260d4feb2932345188e50f65c798db1e8bb4", "mmlu_miscellaneous": "50d1ec8566cca1585a54310882df59a1a36d12921a2c54eb50f5d8cd43671470", "mmlu_management": "21dc8d1b1528148e3e5eab8e5b2e9e1cd69513c82a87509bb777c44fbcf06684", "mmlu_college_medicine": "14529d73333850b8be0fc1d4c102c4500b76434c8c761611be6899af27608455", "mmlu_medical_genetics": "9b736fa6d447dd8f017f7e2dc81e7487f3412a8551075ca312e48db9c4c5e108", "mmlu_professional_accounting": "e37d42330a5af8d569f0a9713de9c729bf3acad5b941d1a94d99367454bf1f5e", "mmlu_virology": "ddac9a6463dfa4d91ade252fcca4b74d91d72a4d7b26dae24bd9e3fd69cc6ab1", "mmlu_high_school_government_and_politics": "83f0261792e1d7045e66cbff5c00e9c3a515d509b5289edc8b86afd55bf5c040", "mmlu_human_sexuality": "7604529311a8c33437ec37d29eee91d421a9d9076978761eff23632ad7e01e2d", "mmlu_high_school_psychology": "c31c14be9ba52af0c00b299cd1a23e9c2bc6b58ad9bd1add9f0e7cd8c4b8f26e", "mmlu_sociology": "dba3af859d4a1892e17fa154a7e28c8443a38df517518fe41ad5f477c59aafb5", "mmlu_high_school_macroeconomics": "1347c24ea6e4de5497b8f15c93253c347014ac11e2673eab6bebee69ee3cd60b", "mmlu_us_foreign_policy": "e9f167f26afe88fb4ed49f9220279bf0488b7f91635b9852fb57b78acea6830d", "mmlu_high_school_geography": "5324a0d02e70d093d0205e24c6e9fdd08e70bae33d2bb8f7de23ad11a98de706", "mmlu_public_relations": "42cede91b1bc0c4814d1489f3ee115fb4a4553e71e9bec3c786ffdf481016605", "mmlu_professional_psychology": "b4d03640e1e416075995ad4e405b94f803abde50471e95a1b76af13d43423138", "mmlu_high_school_microeconomics": "8c4f05dcc2d4cb5cb12d795a01721ac214435e2727c079828a1e181f9520c4e2", "mmlu_security_studies": "67977d134979b89d013f2219feabde20d42a53c8b011e19883b82ff1adc53a53", "mmlu_econometrics": "62edd95ee828a143df05736ad152a13aeb06e5ad72f806a26b82f2bc23b7b96e", "mmlu_high_school_world_history": "ed0f7014f54490189a3314ece657db77d28c1d80d182d061d53e7dd5038bfa17", "mmlu_high_school_european_history": "6d2776b2a93371215b91173033622c3ac6eecd62b344806259cc88e6a87af105", "mmlu_high_school_us_history": "3f974bbd34dd5fd88eca6d39b3adcfba9a397892f8a361ab421550554bceced0", "mmlu_logical_fallacies": "a1f7d58d172d3a3fe8725432d03bcc7e20beb3cad8d53b671298777d13a989b8", "mmlu_moral_scenarios": "cc0ebef61f42135e2a01adfbda1487c34d90050f053e65392546e7dfdab4da70", "mmlu_formal_logic": "d3d2b48bf6e87059cd113f7cbad53dc846191b9c7f46658f2fa83a772a8943f4", "mmlu_moral_disputes": "47393c3796d5c0ca3c6cb26967667b5e2b8fdf16e82af39e15de44ad510af169", "mmlu_prehistory": "5a23a5a7ca9bb1eba10d3efe09f5f9cf973c19344bce299a944288ea1ba257a4", "mmlu_world_religions": "71ce37f2bfc410129589c84784ff6307ff34cb28fbc7f3472322166d71def5bf", "mmlu_philosophy": "dcde538e417b322195cb862c260c735ae6908adaef15bfb03e23e9ca407797fe", "mmlu_jurisprudence": "18267944042c67ccbc3951e9caf555e7fc470edb55380aea8267e6ec0932e56c", "mmlu_international_law": "0cb13702f8813cd46e74859a47a1f380fa344240d4e7fd16811171f08f41ce08", "mmlu_professional_law": "f43120983c735793b59ddf88207e1e0009f26e198b1efa8315c0f39138e2f7e4" }, "model_source": "hf", "model_name": "inceptionai/jais-adapted-70b-chat", "model_name_sanitized": "inceptionai__jais-adapted-70b-chat", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 361151.154868588, "end_time": 364064.686803542, "total_evaluation_time_seconds": "2913.531934953993" }