| { | |
| "results": { | |
| "mmlu": { | |
| "acc,none": 0.6513317191283293, | |
| "acc_stderr,none": 0.0038015515470113683, | |
| "alias": "mmlu" | |
| }, | |
| "mmlu_humanities": { | |
| "acc,none": 0.5991498405951116, | |
| "acc_stderr,none": 0.006795686556137054, | |
| "alias": " - humanities" | |
| }, | |
| "mmlu_formal_logic": { | |
| "alias": " - formal_logic", | |
| "acc,none": 0.48412698412698413, | |
| "acc_stderr,none": 0.04469881854072606 | |
| }, | |
| "mmlu_high_school_european_history": { | |
| "alias": " - high_school_european_history", | |
| "acc,none": 0.7757575757575758, | |
| "acc_stderr,none": 0.03256866661681102 | |
| }, | |
| "mmlu_high_school_us_history": { | |
| "alias": " - high_school_us_history", | |
| "acc,none": 0.8137254901960784, | |
| "acc_stderr,none": 0.027325470966716326 | |
| }, | |
| "mmlu_high_school_world_history": { | |
| "alias": " - high_school_world_history", | |
| "acc,none": 0.8185654008438819, | |
| "acc_stderr,none": 0.02508596114457966 | |
| }, | |
| "mmlu_international_law": { | |
| "alias": " - international_law", | |
| "acc,none": 0.8181818181818182, | |
| "acc_stderr,none": 0.03520893951097653 | |
| }, | |
| "mmlu_jurisprudence": { | |
| "alias": " - jurisprudence", | |
| "acc,none": 0.7314814814814815, | |
| "acc_stderr,none": 0.042844679680521934 | |
| }, | |
| "mmlu_logical_fallacies": { | |
| "alias": " - logical_fallacies", | |
| "acc,none": 0.7484662576687117, | |
| "acc_stderr,none": 0.034089978868575295 | |
| }, | |
| "mmlu_moral_disputes": { | |
| "alias": " - moral_disputes", | |
| "acc,none": 0.7254335260115607, | |
| "acc_stderr,none": 0.024027745155265016 | |
| }, | |
| "mmlu_moral_scenarios": { | |
| "alias": " - moral_scenarios", | |
| "acc,none": 0.4145251396648045, | |
| "acc_stderr,none": 0.016476342210254 | |
| }, | |
| "mmlu_philosophy": { | |
| "alias": " - philosophy", | |
| "acc,none": 0.7266881028938906, | |
| "acc_stderr,none": 0.025311765975426108 | |
| }, | |
| "mmlu_prehistory": { | |
| "alias": " - prehistory", | |
| "acc,none": 0.7191358024691358, | |
| "acc_stderr,none": 0.025006469755799204 | |
| }, | |
| "mmlu_professional_law": { | |
| "alias": " - professional_law", | |
| "acc,none": 0.4895697522816167, | |
| "acc_stderr,none": 0.012767457253930643 | |
| }, | |
| "mmlu_world_religions": { | |
| "alias": " - world_religions", | |
| "acc,none": 0.8070175438596491, | |
| "acc_stderr,none": 0.030267457554898458 | |
| }, | |
| "mmlu_other": { | |
| "acc,none": 0.7203089797232056, | |
| "acc_stderr,none": 0.007721341849715981, | |
| "alias": " - other" | |
| }, | |
| "mmlu_business_ethics": { | |
| "alias": " - business_ethics", | |
| "acc,none": 0.64, | |
| "acc_stderr,none": 0.04824181513244218 | |
| }, | |
| "mmlu_clinical_knowledge": { | |
| "alias": " - clinical_knowledge", | |
| "acc,none": 0.7509433962264151, | |
| "acc_stderr,none": 0.02661648298050172 | |
| }, | |
| "mmlu_college_medicine": { | |
| "alias": " - college_medicine", | |
| "acc,none": 0.6473988439306358, | |
| "acc_stderr,none": 0.036430371689585475 | |
| }, | |
| "mmlu_global_facts": { | |
| "alias": " - global_facts", | |
| "acc,none": 0.32, | |
| "acc_stderr,none": 0.04688261722621505 | |
| }, | |
| "mmlu_human_aging": { | |
| "alias": " - human_aging", | |
| "acc,none": 0.6995515695067265, | |
| "acc_stderr,none": 0.030769352008229132 | |
| }, | |
| "mmlu_management": { | |
| "alias": " - management", | |
| "acc,none": 0.8543689320388349, | |
| "acc_stderr,none": 0.03492606476623789 | |
| }, | |
| "mmlu_marketing": { | |
| "alias": " - marketing", | |
| "acc,none": 0.8632478632478633, | |
| "acc_stderr,none": 0.02250903393707781 | |
| }, | |
| "mmlu_medical_genetics": { | |
| "alias": " - medical_genetics", | |
| "acc,none": 0.83, | |
| "acc_stderr,none": 0.0377525168068637 | |
| }, | |
| "mmlu_miscellaneous": { | |
| "alias": " - miscellaneous", | |
| "acc,none": 0.8122605363984674, | |
| "acc_stderr,none": 0.013964393769899122 | |
| }, | |
| "mmlu_nutrition": { | |
| "alias": " - nutrition", | |
| "acc,none": 0.7973856209150327, | |
| "acc_stderr,none": 0.023015446877985655 | |
| }, | |
| "mmlu_professional_accounting": { | |
| "alias": " - professional_accounting", | |
| "acc,none": 0.48936170212765956, | |
| "acc_stderr,none": 0.02982074719142248 | |
| }, | |
| "mmlu_professional_medicine": { | |
| "alias": " - professional_medicine", | |
| "acc,none": 0.6911764705882353, | |
| "acc_stderr,none": 0.028064998167040094 | |
| }, | |
| "mmlu_virology": { | |
| "alias": " - virology", | |
| "acc,none": 0.5783132530120482, | |
| "acc_stderr,none": 0.03844453181770917 | |
| }, | |
| "mmlu_social_sciences": { | |
| "acc,none": 0.7604809879753006, | |
| "acc_stderr,none": 0.007519143818000645, | |
| "alias": " - social sciences" | |
| }, | |
| "mmlu_econometrics": { | |
| "alias": " - econometrics", | |
| "acc,none": 0.49122807017543857, | |
| "acc_stderr,none": 0.04702880432049615 | |
| }, | |
| "mmlu_high_school_geography": { | |
| "alias": " - high_school_geography", | |
| "acc,none": 0.8131313131313131, | |
| "acc_stderr,none": 0.02777253333421899 | |
| }, | |
| "mmlu_high_school_government_and_politics": { | |
| "alias": " - high_school_government_and_politics", | |
| "acc,none": 0.8808290155440415, | |
| "acc_stderr,none": 0.023381935348121427 | |
| }, | |
| "mmlu_high_school_macroeconomics": { | |
| "alias": " - high_school_macroeconomics", | |
| "acc,none": 0.6461538461538462, | |
| "acc_stderr,none": 0.024243783994062164 | |
| }, | |
| "mmlu_high_school_microeconomics": { | |
| "alias": " - high_school_microeconomics", | |
| "acc,none": 0.7436974789915967, | |
| "acc_stderr,none": 0.02835962087053395 | |
| }, | |
| "mmlu_high_school_psychology": { | |
| "alias": " - high_school_psychology", | |
| "acc,none": 0.8495412844036697, | |
| "acc_stderr,none": 0.015328563932669237 | |
| }, | |
| "mmlu_human_sexuality": { | |
| "alias": " - human_sexuality", | |
| "acc,none": 0.7786259541984732, | |
| "acc_stderr,none": 0.036412970813137296 | |
| }, | |
| "mmlu_professional_psychology": { | |
| "alias": " - professional_psychology", | |
| "acc,none": 0.7156862745098039, | |
| "acc_stderr,none": 0.01824902441120766 | |
| }, | |
| "mmlu_public_relations": { | |
| "alias": " - public_relations", | |
| "acc,none": 0.7090909090909091, | |
| "acc_stderr,none": 0.04350271442923243 | |
| }, | |
| "mmlu_security_studies": { | |
| "alias": " - security_studies", | |
| "acc,none": 0.726530612244898, | |
| "acc_stderr,none": 0.028535560337128445 | |
| }, | |
| "mmlu_sociology": { | |
| "alias": " - sociology", | |
| "acc,none": 0.8805970149253731, | |
| "acc_stderr,none": 0.02292879327721974 | |
| }, | |
| "mmlu_us_foreign_policy": { | |
| "alias": " - us_foreign_policy", | |
| "acc,none": 0.88, | |
| "acc_stderr,none": 0.03265986323710905 | |
| }, | |
| "mmlu_stem": { | |
| "acc,none": 0.5547098001902949, | |
| "acc_stderr,none": 0.008489551836827522, | |
| "alias": " - stem" | |
| }, | |
| "mmlu_abstract_algebra": { | |
| "alias": " - abstract_algebra", | |
| "acc,none": 0.3, | |
| "acc_stderr,none": 0.046056618647183814 | |
| }, | |
| "mmlu_anatomy": { | |
| "alias": " - anatomy", | |
| "acc,none": 0.6296296296296297, | |
| "acc_stderr,none": 0.041716541613545426 | |
| }, | |
| "mmlu_astronomy": { | |
| "alias": " - astronomy", | |
| "acc,none": 0.7105263157894737, | |
| "acc_stderr,none": 0.036906779861372814 | |
| }, | |
| "mmlu_college_biology": { | |
| "alias": " - college_biology", | |
| "acc,none": 0.7708333333333334, | |
| "acc_stderr,none": 0.035146974678623884 | |
| }, | |
| "mmlu_college_chemistry": { | |
| "alias": " - college_chemistry", | |
| "acc,none": 0.44, | |
| "acc_stderr,none": 0.04988876515698589 | |
| }, | |
| "mmlu_college_computer_science": { | |
| "alias": " - college_computer_science", | |
| "acc,none": 0.49, | |
| "acc_stderr,none": 0.05024183937956912 | |
| }, | |
| "mmlu_college_mathematics": { | |
| "alias": " - college_mathematics", | |
| "acc,none": 0.32, | |
| "acc_stderr,none": 0.04688261722621504 | |
| }, | |
| "mmlu_college_physics": { | |
| "alias": " - college_physics", | |
| "acc,none": 0.4803921568627451, | |
| "acc_stderr,none": 0.04971358884367406 | |
| }, | |
| "mmlu_computer_security": { | |
| "alias": " - computer_security", | |
| "acc,none": 0.84, | |
| "acc_stderr,none": 0.03684529491774708 | |
| }, | |
| "mmlu_conceptual_physics": { | |
| "alias": " - conceptual_physics", | |
| "acc,none": 0.6085106382978723, | |
| "acc_stderr,none": 0.03190701242326812 | |
| }, | |
| "mmlu_electrical_engineering": { | |
| "alias": " - electrical_engineering", | |
| "acc,none": 0.6137931034482759, | |
| "acc_stderr,none": 0.04057324734419036 | |
| }, | |
| "mmlu_elementary_mathematics": { | |
| "alias": " - elementary_mathematics", | |
| "acc,none": 0.4365079365079365, | |
| "acc_stderr,none": 0.0255428468174005 | |
| }, | |
| "mmlu_high_school_biology": { | |
| "alias": " - high_school_biology", | |
| "acc,none": 0.7806451612903226, | |
| "acc_stderr,none": 0.023540799358723295 | |
| }, | |
| "mmlu_high_school_chemistry": { | |
| "alias": " - high_school_chemistry", | |
| "acc,none": 0.5320197044334976, | |
| "acc_stderr,none": 0.03510766597959215 | |
| }, | |
| "mmlu_high_school_computer_science": { | |
| "alias": " - high_school_computer_science", | |
| "acc,none": 0.67, | |
| "acc_stderr,none": 0.04725815626252607 | |
| }, | |
| "mmlu_high_school_mathematics": { | |
| "alias": " - high_school_mathematics", | |
| "acc,none": 0.4074074074074074, | |
| "acc_stderr,none": 0.029958249250082114 | |
| }, | |
| "mmlu_high_school_physics": { | |
| "alias": " - high_school_physics", | |
| "acc,none": 0.44370860927152317, | |
| "acc_stderr,none": 0.04056527902281732 | |
| }, | |
| "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": 0.4375, | |
| "acc_stderr,none": 0.04708567521880525 | |
| } | |
| }, | |
| "groups": { | |
| "mmlu": { | |
| "acc,none": 0.6513317191283293, | |
| "acc_stderr,none": 0.0038015515470113683, | |
| "alias": "mmlu" | |
| }, | |
| "mmlu_humanities": { | |
| "acc,none": 0.5991498405951116, | |
| "acc_stderr,none": 0.006795686556137054, | |
| "alias": " - humanities" | |
| }, | |
| "mmlu_other": { | |
| "acc,none": 0.7203089797232056, | |
| "acc_stderr,none": 0.007721341849715981, | |
| "alias": " - other" | |
| }, | |
| "mmlu_social_sciences": { | |
| "acc,none": 0.7604809879753006, | |
| "acc_stderr,none": 0.007519143818000645, | |
| "alias": " - social sciences" | |
| }, | |
| "mmlu_stem": { | |
| "acc,none": 0.5547098001902949, | |
| "acc_stderr,none": 0.008489551836827522, | |
| "alias": " - stem" | |
| } | |
| }, | |
| "group_subtasks": { | |
| "mmlu_humanities": [ | |
| "mmlu_high_school_european_history", | |
| "mmlu_high_school_world_history", | |
| "mmlu_logical_fallacies", | |
| "mmlu_world_religions", | |
| "mmlu_moral_scenarios", | |
| "mmlu_formal_logic", | |
| "mmlu_high_school_us_history", | |
| "mmlu_international_law", | |
| "mmlu_prehistory", | |
| "mmlu_philosophy", | |
| "mmlu_moral_disputes", | |
| "mmlu_jurisprudence", | |
| "mmlu_professional_law" | |
| ], | |
| "mmlu_social_sciences": [ | |
| "mmlu_sociology", | |
| "mmlu_high_school_government_and_politics", | |
| "mmlu_security_studies", | |
| "mmlu_professional_psychology", | |
| "mmlu_high_school_macroeconomics", | |
| "mmlu_us_foreign_policy", | |
| "mmlu_high_school_microeconomics", | |
| "mmlu_econometrics", | |
| "mmlu_high_school_geography", | |
| "mmlu_human_sexuality", | |
| "mmlu_public_relations", | |
| "mmlu_high_school_psychology" | |
| ], | |
| "mmlu_other": [ | |
| "mmlu_marketing", | |
| "mmlu_miscellaneous", | |
| "mmlu_clinical_knowledge", | |
| "mmlu_management", | |
| "mmlu_human_aging", | |
| "mmlu_medical_genetics", | |
| "mmlu_business_ethics", | |
| "mmlu_global_facts", | |
| "mmlu_virology", | |
| "mmlu_professional_accounting", | |
| "mmlu_nutrition", | |
| "mmlu_professional_medicine", | |
| "mmlu_college_medicine" | |
| ], | |
| "mmlu_stem": [ | |
| "mmlu_college_chemistry", | |
| "mmlu_college_physics", | |
| "mmlu_high_school_computer_science", | |
| "mmlu_abstract_algebra", | |
| "mmlu_high_school_biology", | |
| "mmlu_college_computer_science", | |
| "mmlu_college_mathematics", | |
| "mmlu_high_school_physics", | |
| "mmlu_high_school_statistics", | |
| "mmlu_high_school_chemistry", | |
| "mmlu_high_school_mathematics", | |
| "mmlu_electrical_engineering", | |
| "mmlu_anatomy", | |
| "mmlu_elementary_mathematics", | |
| "mmlu_computer_security", | |
| "mmlu_college_biology", | |
| "mmlu_conceptual_physics", | |
| "mmlu_astronomy", | |
| "mmlu_machine_learning" | |
| ], | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "mmlu_anatomy": 5, | |
| "mmlu_astronomy": 5, | |
| "mmlu_business_ethics": 5, | |
| "mmlu_clinical_knowledge": 5, | |
| "mmlu_college_biology": 5, | |
| "mmlu_college_chemistry": 5, | |
| "mmlu_college_computer_science": 5, | |
| "mmlu_college_mathematics": 5, | |
| "mmlu_college_medicine": 5, | |
| "mmlu_college_physics": 5, | |
| "mmlu_computer_security": 5, | |
| "mmlu_conceptual_physics": 5, | |
| "mmlu_econometrics": 5, | |
| "mmlu_electrical_engineering": 5, | |
| "mmlu_elementary_mathematics": 5, | |
| "mmlu_formal_logic": 5, | |
| "mmlu_global_facts": 5, | |
| "mmlu_high_school_biology": 5, | |
| "mmlu_high_school_chemistry": 5, | |
| "mmlu_high_school_computer_science": 5, | |
| "mmlu_high_school_european_history": 5, | |
| "mmlu_high_school_geography": 5, | |
| "mmlu_high_school_government_and_politics": 5, | |
| "mmlu_high_school_macroeconomics": 5, | |
| "mmlu_high_school_mathematics": 5, | |
| "mmlu_high_school_microeconomics": 5, | |
| "mmlu_high_school_physics": 5, | |
| "mmlu_high_school_psychology": 5, | |
| "mmlu_high_school_statistics": 5, | |
| "mmlu_high_school_us_history": 5, | |
| "mmlu_high_school_world_history": 5, | |
| "mmlu_human_aging": 5, | |
| "mmlu_human_sexuality": 5, | |
| "mmlu_international_law": 5, | |
| "mmlu_jurisprudence": 5, | |
| "mmlu_logical_fallacies": 5, | |
| "mmlu_machine_learning": 5, | |
| "mmlu_management": 5, | |
| "mmlu_marketing": 5, | |
| "mmlu_medical_genetics": 5, | |
| "mmlu_miscellaneous": 5, | |
| "mmlu_moral_disputes": 5, | |
| "mmlu_moral_scenarios": 5, | |
| "mmlu_nutrition": 5, | |
| "mmlu_philosophy": 5, | |
| "mmlu_prehistory": 5, | |
| "mmlu_professional_accounting": 5, | |
| "mmlu_professional_law": 5, | |
| "mmlu_professional_medicine": 5, | |
| "mmlu_professional_psychology": 5, | |
| "mmlu_public_relations": 5, | |
| "mmlu_security_studies": 5, | |
| "mmlu_sociology": 5, | |
| "mmlu_us_foreign_policy": 5, | |
| "mmlu_virology": 5, | |
| "mmlu_world_religions": 5 | |
| }, | |
| "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_college_chemistry": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_college_physics": { | |
| "original": 102, | |
| "effective": 102 | |
| }, | |
| "mmlu_high_school_computer_science": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_abstract_algebra": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_high_school_biology": { | |
| "original": 310, | |
| "effective": 310 | |
| }, | |
| "mmlu_college_computer_science": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_college_mathematics": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_high_school_physics": { | |
| "original": 151, | |
| "effective": 151 | |
| }, | |
| "mmlu_high_school_statistics": { | |
| "original": 216, | |
| "effective": 216 | |
| }, | |
| "mmlu_high_school_chemistry": { | |
| "original": 203, | |
| "effective": 203 | |
| }, | |
| "mmlu_high_school_mathematics": { | |
| "original": 270, | |
| "effective": 270 | |
| }, | |
| "mmlu_electrical_engineering": { | |
| "original": 145, | |
| "effective": 145 | |
| }, | |
| "mmlu_anatomy": { | |
| "original": 135, | |
| "effective": 135 | |
| }, | |
| "mmlu_elementary_mathematics": { | |
| "original": 378, | |
| "effective": 378 | |
| }, | |
| "mmlu_computer_security": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_college_biology": { | |
| "original": 144, | |
| "effective": 144 | |
| }, | |
| "mmlu_conceptual_physics": { | |
| "original": 235, | |
| "effective": 235 | |
| }, | |
| "mmlu_astronomy": { | |
| "original": 152, | |
| "effective": 152 | |
| }, | |
| "mmlu_machine_learning": { | |
| "original": 112, | |
| "effective": 112 | |
| }, | |
| "mmlu_marketing": { | |
| "original": 234, | |
| "effective": 234 | |
| }, | |
| "mmlu_miscellaneous": { | |
| "original": 783, | |
| "effective": 783 | |
| }, | |
| "mmlu_clinical_knowledge": { | |
| "original": 265, | |
| "effective": 265 | |
| }, | |
| "mmlu_management": { | |
| "original": 103, | |
| "effective": 103 | |
| }, | |
| "mmlu_human_aging": { | |
| "original": 223, | |
| "effective": 223 | |
| }, | |
| "mmlu_medical_genetics": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_business_ethics": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_global_facts": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_virology": { | |
| "original": 166, | |
| "effective": 166 | |
| }, | |
| "mmlu_professional_accounting": { | |
| "original": 282, | |
| "effective": 282 | |
| }, | |
| "mmlu_nutrition": { | |
| "original": 306, | |
| "effective": 306 | |
| }, | |
| "mmlu_professional_medicine": { | |
| "original": 272, | |
| "effective": 272 | |
| }, | |
| "mmlu_college_medicine": { | |
| "original": 173, | |
| "effective": 173 | |
| }, | |
| "mmlu_sociology": { | |
| "original": 201, | |
| "effective": 201 | |
| }, | |
| "mmlu_high_school_government_and_politics": { | |
| "original": 193, | |
| "effective": 193 | |
| }, | |
| "mmlu_security_studies": { | |
| "original": 245, | |
| "effective": 245 | |
| }, | |
| "mmlu_professional_psychology": { | |
| "original": 612, | |
| "effective": 612 | |
| }, | |
| "mmlu_high_school_macroeconomics": { | |
| "original": 390, | |
| "effective": 390 | |
| }, | |
| "mmlu_us_foreign_policy": { | |
| "original": 100, | |
| "effective": 100 | |
| }, | |
| "mmlu_high_school_microeconomics": { | |
| "original": 238, | |
| "effective": 238 | |
| }, | |
| "mmlu_econometrics": { | |
| "original": 114, | |
| "effective": 114 | |
| }, | |
| "mmlu_high_school_geography": { | |
| "original": 198, | |
| "effective": 198 | |
| }, | |
| "mmlu_human_sexuality": { | |
| "original": 131, | |
| "effective": 131 | |
| }, | |
| "mmlu_public_relations": { | |
| "original": 110, | |
| "effective": 110 | |
| }, | |
| "mmlu_high_school_psychology": { | |
| "original": 545, | |
| "effective": 545 | |
| }, | |
| "mmlu_high_school_european_history": { | |
| "original": 165, | |
| "effective": 165 | |
| }, | |
| "mmlu_high_school_world_history": { | |
| "original": 237, | |
| "effective": 237 | |
| }, | |
| "mmlu_logical_fallacies": { | |
| "original": 163, | |
| "effective": 163 | |
| }, | |
| "mmlu_world_religions": { | |
| "original": 171, | |
| "effective": 171 | |
| }, | |
| "mmlu_moral_scenarios": { | |
| "original": 895, | |
| "effective": 895 | |
| }, | |
| "mmlu_formal_logic": { | |
| "original": 126, | |
| "effective": 126 | |
| }, | |
| "mmlu_high_school_us_history": { | |
| "original": 204, | |
| "effective": 204 | |
| }, | |
| "mmlu_international_law": { | |
| "original": 121, | |
| "effective": 121 | |
| }, | |
| "mmlu_prehistory": { | |
| "original": 324, | |
| "effective": 324 | |
| }, | |
| "mmlu_philosophy": { | |
| "original": 311, | |
| "effective": 311 | |
| }, | |
| "mmlu_moral_disputes": { | |
| "original": 346, | |
| "effective": 346 | |
| }, | |
| "mmlu_jurisprudence": { | |
| "original": 108, | |
| "effective": 108 | |
| }, | |
| "mmlu_professional_law": { | |
| "original": 1534, | |
| "effective": 1534 | |
| } | |
| }, | |
| "config": { | |
| "model": "hf", | |
| "model_args": "pretrained=/data2/vchua/run/hgx1-240823-wanda/wanda-ed/meta-llama/Meta-Llama-3.1-8B-wanda-unstructured-0.0,dtype=bfloat16", | |
| "model_num_parameters": 8030261248, | |
| "model_dtype": "torch.bfloat16", | |
| "model_revision": "main", | |
| "model_sha": "", | |
| "batch_size": "auto", | |
| "batch_sizes": [ | |
| 8 | |
| ], | |
| "device": "cuda:3", | |
| "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": null, | |
| "date": 1726203724.6020887, | |
| "pretty_env_info": "PyTorch version: 2.4.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 20.04.6 LTS (x86_64)\nGCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0\nClang version: Could not collect\nCMake version: version 3.26.0\nLibc version: glibc-2.31\n\nPython version: 3.11.10 | packaged by conda-forge | (main, Sep 10 2024, 11:01:28) [GCC 13.3.0] (64-bit runtime)\nPython platform: Linux-5.4.0-182-generic-x86_64-with-glibc2.31\nIs CUDA available: True\nCUDA runtime version: Could not collect\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\n\nNvidia driver version: 555.42.02\ncuDNN version: Could not collect\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\nByte Order: Little Endian\nAddress sizes: 46 bits physical, 57 bits virtual\nCPU(s): 64\nOn-line CPU(s) list: 0-63\nThread(s) per core: 2\nCore(s) per socket: 16\nSocket(s): 2\nNUMA node(s): 2\nVendor ID: GenuineIntel\nCPU family: 6\nModel: 106\nModel name: Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz\nStepping: 6\nFrequency boost: enabled\nCPU MHz: 800.000\nCPU max MHz: 3600.0000\nCPU min MHz: 800.0000\nBogoMIPS: 6200.00\nVirtualization: VT-x\nL1d cache: 1.5 MiB\nL1i cache: 1 MiB\nL2 cache: 40 MiB\nL3 cache: 72 MiB\nNUMA node0 CPU(s): 0-15,32-47\nNUMA node1 CPU(s): 16-31,48-63\nVulnerability Gather data sampling: Mitigation; Microcode\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable\nVulnerability Retbleed: Not affected\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; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid md_clear pconfig flush_l1d arch_capabilities\n\nVersions of relevant libraries:\n[pip3] numpy==2.1.1\n[pip3] torch==2.4.1\n[pip3] triton==3.0.0\n[conda] numpy 2.1.1 pypi_0 pypi\n[conda] torch 2.4.1 pypi_0 pypi\n[conda] triton 3.0.0 pypi_0 pypi", | |
| "transformers_version": "4.44.2", | |
| "upper_git_hash": null, | |
| "tokenizer_pad_token": [ | |
| "<|end_of_text|>", | |
| "128001" | |
| ], | |
| "tokenizer_eos_token": [ | |
| "<|end_of_text|>", | |
| "128001" | |
| ], | |
| "tokenizer_bos_token": [ | |
| "<|begin_of_text|>", | |
| "128000" | |
| ], | |
| "eot_token_id": 128001, | |
| "max_length": 131072, | |
| "task_hashes": {}, | |
| "model_source": "hf", | |
| "model_name": "/data2/vchua/run/hgx1-240823-wanda/wanda-ed/meta-llama/Meta-Llama-3.1-8B-wanda-unstructured-0.0", | |
| "model_name_sanitized": "__data2__vchua__run__hgx1-240823-wanda__wanda-ed__meta-llama__Meta-Llama-3.1-8B-wanda-unstructured-0.0", | |
| "system_instruction": null, | |
| "system_instruction_sha": null, | |
| "fewshot_as_multiturn": false, | |
| "chat_template": null, | |
| "chat_template_sha": null, | |
| "start_time": 9018236.178386472, | |
| "end_time": 9019273.06490568, | |
| "total_evaluation_time_seconds": "1036.8865192085505" | |
| } |