{ "results": { "mmlu": { "acc,none": 0.5438683948155534, "acc_stderr,none": 0.004046605401658642, "alias": "mmlu" }, "mmlu_humanities": { "alias": " - humanities", "acc,none": 0.4973432518597237, "acc_stderr,none": 0.0069921729107274965 }, "mmlu_formal_logic": { "alias": " - formal_logic", "acc,none": 0.36507936507936506, "acc_stderr,none": 0.04306241259127153 }, "mmlu_high_school_european_history": { "alias": " - high_school_european_history", "acc,none": 0.6484848484848484, "acc_stderr,none": 0.0372820699868265 }, "mmlu_high_school_us_history": { "alias": " - high_school_us_history", "acc,none": 0.6764705882352942, "acc_stderr,none": 0.03283472056108561 }, "mmlu_high_school_world_history": { "alias": " - high_school_world_history", "acc,none": 0.7088607594936709, "acc_stderr,none": 0.029571601065753374 }, "mmlu_international_law": { "alias": " - international_law", "acc,none": 0.6942148760330579, "acc_stderr,none": 0.04205953933884124 }, "mmlu_jurisprudence": { "alias": " - jurisprudence", "acc,none": 0.6851851851851852, "acc_stderr,none": 0.04489931073591312 }, "mmlu_logical_fallacies": { "alias": " - logical_fallacies", "acc,none": 0.7116564417177914, "acc_stderr,none": 0.035590395316173425 }, "mmlu_moral_disputes": { "alias": " - moral_disputes", "acc,none": 0.630057803468208, "acc_stderr,none": 0.025992472029306383 }, "mmlu_moral_scenarios": { "alias": " - moral_scenarios", "acc,none": 0.3195530726256983, "acc_stderr,none": 0.015595520294147402 }, "mmlu_philosophy": { "alias": " - philosophy", "acc,none": 0.594855305466238, "acc_stderr,none": 0.027882383791325953 }, "mmlu_prehistory": { "alias": " - prehistory", "acc,none": 0.5524691358024691, "acc_stderr,none": 0.027667138569422715 }, "mmlu_professional_law": { "alias": " - professional_law", "acc,none": 0.4048239895697523, "acc_stderr,none": 0.012536743830953994 }, "mmlu_world_religions": { "alias": " - world_religions", "acc,none": 0.6900584795321637, "acc_stderr,none": 0.035469769593931624 }, "mmlu_other": { "alias": " - other", "acc,none": 0.5909237206308336, "acc_stderr,none": 0.008549729756636936 }, "mmlu_business_ethics": { "alias": " - business_ethics", "acc,none": 0.61, "acc_stderr,none": 0.04902071300001974 }, "mmlu_clinical_knowledge": { "alias": " - clinical_knowledge", "acc,none": 0.5735849056603773, "acc_stderr,none": 0.030437794342983042 }, "mmlu_college_medicine": { "alias": " - college_medicine", "acc,none": 0.49710982658959535, "acc_stderr,none": 0.038124005659748335 }, "mmlu_global_facts": { "alias": " - global_facts", "acc,none": 0.34, "acc_stderr,none": 0.04760952285695235 }, "mmlu_human_aging": { "alias": " - human_aging", "acc,none": 0.5964125560538116, "acc_stderr,none": 0.032928028193303135 }, "mmlu_management": { "alias": " - management", "acc,none": 0.7669902912621359, "acc_stderr,none": 0.04185832598928315 }, "mmlu_marketing": { "alias": " - marketing", "acc,none": 0.8076923076923077, "acc_stderr,none": 0.025819233256483727 }, "mmlu_medical_genetics": { "alias": " - medical_genetics", "acc,none": 0.56, "acc_stderr,none": 0.04988876515698589 }, "mmlu_miscellaneous": { "alias": " - miscellaneous", "acc,none": 0.6845466155810983, "acc_stderr,none": 0.016617501738763397 }, "mmlu_nutrition": { "alias": " - nutrition", "acc,none": 0.6503267973856209, "acc_stderr,none": 0.0273053080762747 }, "mmlu_professional_accounting": { "alias": " - professional_accounting", "acc,none": 0.42907801418439717, "acc_stderr,none": 0.02952591430255855 }, "mmlu_professional_medicine": { "alias": " - professional_medicine", "acc,none": 0.4338235294117647, "acc_stderr,none": 0.03010563657001664 }, "mmlu_virology": { "alias": " - virology", "acc,none": 0.43373493975903615, "acc_stderr,none": 0.03858158940685515 }, "mmlu_social_sciences": { "alias": " - social_sciences", "acc,none": 0.6360090997725056, "acc_stderr,none": 0.008459352068826637 }, "mmlu_econometrics": { "alias": " - econometrics", "acc,none": 0.34210526315789475, "acc_stderr,none": 0.04462917535336936 }, "mmlu_high_school_geography": { "alias": " - high_school_geography", "acc,none": 0.7272727272727273, "acc_stderr,none": 0.03173071239071724 }, "mmlu_high_school_government_and_politics": { "alias": " - high_school_government_and_politics", "acc,none": 0.7979274611398963, "acc_stderr,none": 0.02897908979429673 }, "mmlu_high_school_macroeconomics": { "alias": " - high_school_macroeconomics", "acc,none": 0.5384615384615384, "acc_stderr,none": 0.025275892070240644 }, "mmlu_high_school_microeconomics": { "alias": " - high_school_microeconomics", "acc,none": 0.6176470588235294, "acc_stderr,none": 0.03156663099215416 }, "mmlu_high_school_psychology": { "alias": " - high_school_psychology", "acc,none": 0.7321100917431193, "acc_stderr,none": 0.018987462257978652 }, "mmlu_human_sexuality": { "alias": " - human_sexuality", "acc,none": 0.6412213740458015, "acc_stderr,none": 0.04206739313864908 }, "mmlu_professional_psychology": { "alias": " - professional_psychology", "acc,none": 0.5294117647058824, "acc_stderr,none": 0.020192808271433788 }, "mmlu_public_relations": { "alias": " - public_relations", "acc,none": 0.5636363636363636, "acc_stderr,none": 0.04750185058907296 }, "mmlu_security_studies": { "alias": " - security_studies", "acc,none": 0.689795918367347, "acc_stderr,none": 0.02961345987248438 }, "mmlu_sociology": { "alias": " - sociology", "acc,none": 0.736318407960199, "acc_stderr,none": 0.031157150869355568 }, "mmlu_us_foreign_policy": { "alias": " - us_foreign_policy", "acc,none": 0.77, "acc_stderr,none": 0.042295258468165044 }, "mmlu_stem": { "alias": " - stem", "acc,none": 0.4770060260069775, "acc_stderr,none": 0.00876253277535237 }, "mmlu_abstract_algebra": { "alias": " - abstract_algebra", "acc,none": 0.38, "acc_stderr,none": 0.04878317312145633 }, "mmlu_anatomy": { "alias": " - anatomy", "acc,none": 0.4666666666666667, "acc_stderr,none": 0.043097329010363554 }, "mmlu_astronomy": { "alias": " - astronomy", "acc,none": 0.5526315789473685, "acc_stderr,none": 0.04046336883978251 }, "mmlu_college_biology": { "alias": " - college_biology", "acc,none": 0.5486111111111112, "acc_stderr,none": 0.04161402398403279 }, "mmlu_college_chemistry": { "alias": " - college_chemistry", "acc,none": 0.39, "acc_stderr,none": 0.04902071300001975 }, "mmlu_college_computer_science": { "alias": " - college_computer_science", "acc,none": 0.53, "acc_stderr,none": 0.05016135580465919 }, "mmlu_college_mathematics": { "alias": " - college_mathematics", "acc,none": 0.31, "acc_stderr,none": 0.04648231987117316 }, "mmlu_college_physics": { "alias": " - college_physics", "acc,none": 0.37254901960784315, "acc_stderr,none": 0.04810840148082633 }, "mmlu_computer_security": { "alias": " - computer_security", "acc,none": 0.71, "acc_stderr,none": 0.045604802157206845 }, "mmlu_conceptual_physics": { "alias": " - conceptual_physics", "acc,none": 0.4765957446808511, "acc_stderr,none": 0.03265019475033582 }, "mmlu_electrical_engineering": { "alias": " - electrical_engineering", "acc,none": 0.5793103448275863, "acc_stderr,none": 0.0411391498118926 }, "mmlu_elementary_mathematics": { "alias": " - elementary_mathematics", "acc,none": 0.4417989417989418, "acc_stderr,none": 0.025576257061253833 }, "mmlu_high_school_biology": { "alias": " - high_school_biology", "acc,none": 0.6161290322580645, "acc_stderr,none": 0.027666182075539645 }, "mmlu_high_school_chemistry": { "alias": " - high_school_chemistry", "acc,none": 0.46798029556650245, "acc_stderr,none": 0.035107665979592154 }, "mmlu_high_school_computer_science": { "alias": " - high_school_computer_science", "acc,none": 0.56, "acc_stderr,none": 0.04988876515698589 }, "mmlu_high_school_mathematics": { "alias": " - high_school_mathematics", "acc,none": 0.37777777777777777, "acc_stderr,none": 0.029560707392465718 }, "mmlu_high_school_physics": { "alias": " - high_school_physics", "acc,none": 0.33774834437086093, "acc_stderr,none": 0.03861557546255169 }, "mmlu_high_school_statistics": { "alias": " - high_school_statistics", "acc,none": 0.4861111111111111, "acc_stderr,none": 0.03408655867977749 }, "mmlu_machine_learning": { "alias": " - machine_learning", "acc,none": 0.4017857142857143, "acc_stderr,none": 0.04653333146973647 } }, "groups": { "mmlu": { "acc,none": 0.5438683948155534, "acc_stderr,none": 0.004046605401658642, "alias": "mmlu" }, "mmlu_humanities": { "alias": " - humanities", "acc,none": 0.4973432518597237, "acc_stderr,none": 0.0069921729107274965 }, "mmlu_other": { "alias": " - other", "acc,none": 0.5909237206308336, "acc_stderr,none": 0.008549729756636936 }, "mmlu_social_sciences": { "alias": " - social_sciences", "acc,none": 0.6360090997725056, "acc_stderr,none": 0.008459352068826637 }, "mmlu_stem": { "alias": " - stem", "acc,none": 0.4770060260069775, "acc_stderr,none": 0.00876253277535237 } }, "group_subtasks": { "mmlu_stem": [ "mmlu_abstract_algebra", "mmlu_college_biology", "mmlu_high_school_biology", "mmlu_conceptual_physics", "mmlu_computer_security", "mmlu_college_physics", "mmlu_college_chemistry", "mmlu_high_school_statistics", "mmlu_anatomy", "mmlu_high_school_mathematics", "mmlu_machine_learning", "mmlu_high_school_physics", "mmlu_electrical_engineering", "mmlu_college_computer_science", "mmlu_high_school_chemistry", "mmlu_astronomy", "mmlu_high_school_computer_science", "mmlu_elementary_mathematics", "mmlu_college_mathematics" ], "mmlu_other": [ "mmlu_business_ethics", "mmlu_marketing", "mmlu_medical_genetics", "mmlu_clinical_knowledge", "mmlu_global_facts", "mmlu_human_aging", "mmlu_professional_medicine", "mmlu_nutrition", "mmlu_management", "mmlu_college_medicine", "mmlu_professional_accounting", "mmlu_virology", "mmlu_miscellaneous" ], "mmlu_social_sciences": [ "mmlu_public_relations", "mmlu_high_school_macroeconomics", "mmlu_human_sexuality", "mmlu_high_school_geography", "mmlu_high_school_psychology", "mmlu_high_school_microeconomics", "mmlu_high_school_government_and_politics", "mmlu_us_foreign_policy", "mmlu_sociology", "mmlu_security_studies", "mmlu_econometrics", "mmlu_professional_psychology" ], "mmlu_humanities": [ "mmlu_philosophy", "mmlu_logical_fallacies", "mmlu_moral_disputes", "mmlu_jurisprudence", "mmlu_high_school_us_history", "mmlu_high_school_world_history", "mmlu_world_religions", "mmlu_moral_scenarios", "mmlu_prehistory", "mmlu_formal_logic", "mmlu_international_law", "mmlu_professional_law", "mmlu_high_school_european_history" ], "mmlu": [ "mmlu_humanities", "mmlu_social_sciences", "mmlu_other", "mmlu_stem" ] }, "configs": { "mmlu_abstract_algebra": { "task": "mmlu_abstract_algebra", "task_alias": "abstract_algebra", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "abstract_algebra", "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": 0.0 } }, "mmlu_anatomy": { "task": "mmlu_anatomy", "task_alias": "anatomy", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "anatomy", "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": 0.0 } }, "mmlu_astronomy": { "task": "mmlu_astronomy", "task_alias": "astronomy", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "astronomy", "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": 0.0 } }, "mmlu_business_ethics": { "task": "mmlu_business_ethics", "task_alias": "business_ethics", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "business_ethics", "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": 0.0 } }, "mmlu_clinical_knowledge": { "task": "mmlu_clinical_knowledge", "task_alias": "clinical_knowledge", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "clinical_knowledge", "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": 0.0 } }, "mmlu_college_biology": { "task": "mmlu_college_biology", "task_alias": "college_biology", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_biology", "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": 0.0 } }, "mmlu_college_chemistry": { "task": "mmlu_college_chemistry", "task_alias": "college_chemistry", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_chemistry", "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": 0.0 } }, "mmlu_college_computer_science": { "task": "mmlu_college_computer_science", "task_alias": "college_computer_science", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_computer_science", "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": 0.0 } }, "mmlu_college_mathematics": { "task": "mmlu_college_mathematics", "task_alias": "college_mathematics", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_mathematics", "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": 0.0 } }, "mmlu_college_medicine": { "task": "mmlu_college_medicine", "task_alias": "college_medicine", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_medicine", "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": 0.0 } }, "mmlu_college_physics": { "task": "mmlu_college_physics", "task_alias": "college_physics", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "college_physics", "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": 0.0 } }, "mmlu_computer_security": { "task": "mmlu_computer_security", "task_alias": "computer_security", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "computer_security", "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": 0.0 } }, "mmlu_conceptual_physics": { "task": "mmlu_conceptual_physics", "task_alias": "conceptual_physics", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "conceptual_physics", "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": 0.0 } }, "mmlu_econometrics": { "task": "mmlu_econometrics", "task_alias": "econometrics", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "econometrics", "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": 0.0 } }, "mmlu_electrical_engineering": { "task": "mmlu_electrical_engineering", "task_alias": "electrical_engineering", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "electrical_engineering", "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": 0.0 } }, "mmlu_elementary_mathematics": { "task": "mmlu_elementary_mathematics", "task_alias": "elementary_mathematics", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "elementary_mathematics", "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": 0.0 } }, "mmlu_formal_logic": { "task": "mmlu_formal_logic", "task_alias": "formal_logic", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "formal_logic", "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": 0.0 } }, "mmlu_global_facts": { "task": "mmlu_global_facts", "task_alias": "global_facts", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "global_facts", "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": 0.0 } }, "mmlu_high_school_biology": { "task": "mmlu_high_school_biology", "task_alias": "high_school_biology", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_biology", "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": 0.0 } }, "mmlu_high_school_chemistry": { "task": "mmlu_high_school_chemistry", "task_alias": "high_school_chemistry", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_chemistry", "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": 0.0 } }, "mmlu_high_school_computer_science": { "task": "mmlu_high_school_computer_science", "task_alias": "high_school_computer_science", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_computer_science", "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": 0.0 } }, "mmlu_high_school_european_history": { "task": "mmlu_high_school_european_history", "task_alias": "high_school_european_history", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_european_history", "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": 0.0 } }, "mmlu_high_school_geography": { "task": "mmlu_high_school_geography", "task_alias": "high_school_geography", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_geography", "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": 0.0 } }, "mmlu_high_school_government_and_politics": { "task": "mmlu_high_school_government_and_politics", "task_alias": "high_school_government_and_politics", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_government_and_politics", "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": 0.0 } }, "mmlu_high_school_macroeconomics": { "task": "mmlu_high_school_macroeconomics", "task_alias": "high_school_macroeconomics", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_macroeconomics", "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": 0.0 } }, "mmlu_high_school_mathematics": { "task": "mmlu_high_school_mathematics", "task_alias": "high_school_mathematics", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_mathematics", "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": 0.0 } }, "mmlu_high_school_microeconomics": { "task": "mmlu_high_school_microeconomics", "task_alias": "high_school_microeconomics", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_microeconomics", "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": 0.0 } }, "mmlu_high_school_physics": { "task": "mmlu_high_school_physics", "task_alias": "high_school_physics", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_physics", "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": 0.0 } }, "mmlu_high_school_psychology": { "task": "mmlu_high_school_psychology", "task_alias": "high_school_psychology", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_psychology", "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": 0.0 } }, "mmlu_high_school_statistics": { "task": "mmlu_high_school_statistics", "task_alias": "high_school_statistics", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_statistics", "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": 0.0 } }, "mmlu_high_school_us_history": { "task": "mmlu_high_school_us_history", "task_alias": "high_school_us_history", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_us_history", "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": 0.0 } }, "mmlu_high_school_world_history": { "task": "mmlu_high_school_world_history", "task_alias": "high_school_world_history", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "high_school_world_history", "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": 0.0 } }, "mmlu_human_aging": { "task": "mmlu_human_aging", "task_alias": "human_aging", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "human_aging", "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": 0.0 } }, "mmlu_human_sexuality": { "task": "mmlu_human_sexuality", "task_alias": "human_sexuality", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "human_sexuality", "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": 0.0 } }, "mmlu_international_law": { "task": "mmlu_international_law", "task_alias": "international_law", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "international_law", "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": 0.0 } }, "mmlu_jurisprudence": { "task": "mmlu_jurisprudence", "task_alias": "jurisprudence", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "jurisprudence", "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": 0.0 } }, "mmlu_logical_fallacies": { "task": "mmlu_logical_fallacies", "task_alias": "logical_fallacies", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "logical_fallacies", "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": 0.0 } }, "mmlu_machine_learning": { "task": "mmlu_machine_learning", "task_alias": "machine_learning", "group": "mmlu_stem", "group_alias": "stem", "dataset_path": "hails/mmlu_no_train", "dataset_name": "machine_learning", "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": 0.0 } }, "mmlu_management": { "task": "mmlu_management", "task_alias": "management", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "management", "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": 0.0 } }, "mmlu_marketing": { "task": "mmlu_marketing", "task_alias": "marketing", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "marketing", "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": 0.0 } }, "mmlu_medical_genetics": { "task": "mmlu_medical_genetics", "task_alias": "medical_genetics", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "medical_genetics", "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": 0.0 } }, "mmlu_miscellaneous": { "task": "mmlu_miscellaneous", "task_alias": "miscellaneous", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "miscellaneous", "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": 0.0 } }, "mmlu_moral_disputes": { "task": "mmlu_moral_disputes", "task_alias": "moral_disputes", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "moral_disputes", "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": 0.0 } }, "mmlu_moral_scenarios": { "task": "mmlu_moral_scenarios", "task_alias": "moral_scenarios", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "moral_scenarios", "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": 0.0 } }, "mmlu_nutrition": { "task": "mmlu_nutrition", "task_alias": "nutrition", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "nutrition", "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": 0.0 } }, "mmlu_philosophy": { "task": "mmlu_philosophy", "task_alias": "philosophy", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "philosophy", "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": 0.0 } }, "mmlu_prehistory": { "task": "mmlu_prehistory", "task_alias": "prehistory", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "prehistory", "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": 0.0 } }, "mmlu_professional_accounting": { "task": "mmlu_professional_accounting", "task_alias": "professional_accounting", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_accounting", "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": 0.0 } }, "mmlu_professional_law": { "task": "mmlu_professional_law", "task_alias": "professional_law", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_law", "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": 0.0 } }, "mmlu_professional_medicine": { "task": "mmlu_professional_medicine", "task_alias": "professional_medicine", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_medicine", "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": 0.0 } }, "mmlu_professional_psychology": { "task": "mmlu_professional_psychology", "task_alias": "professional_psychology", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "professional_psychology", "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": 0.0 } }, "mmlu_public_relations": { "task": "mmlu_public_relations", "task_alias": "public_relations", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "public_relations", "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": 0.0 } }, "mmlu_security_studies": { "task": "mmlu_security_studies", "task_alias": "security_studies", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "security_studies", "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": 0.0 } }, "mmlu_sociology": { "task": "mmlu_sociology", "task_alias": "sociology", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "sociology", "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": 0.0 } }, "mmlu_us_foreign_policy": { "task": "mmlu_us_foreign_policy", "task_alias": "us_foreign_policy", "group": "mmlu_social_sciences", "group_alias": "social_sciences", "dataset_path": "hails/mmlu_no_train", "dataset_name": "us_foreign_policy", "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": 0.0 } }, "mmlu_virology": { "task": "mmlu_virology", "task_alias": "virology", "group": "mmlu_other", "group_alias": "other", "dataset_path": "hails/mmlu_no_train", "dataset_name": "virology", "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": 0.0 } }, "mmlu_world_religions": { "task": "mmlu_world_religions", "task_alias": "world_religions", "group": "mmlu_humanities", "group_alias": "humanities", "dataset_path": "hails/mmlu_no_train", "dataset_name": "world_religions", "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": 0.0 } } }, "versions": { "mmlu_abstract_algebra": 0.0, "mmlu_anatomy": 0.0, "mmlu_astronomy": 0.0, "mmlu_business_ethics": 0.0, "mmlu_clinical_knowledge": 0.0, "mmlu_college_biology": 0.0, "mmlu_college_chemistry": 0.0, "mmlu_college_computer_science": 0.0, "mmlu_college_mathematics": 0.0, "mmlu_college_medicine": 0.0, "mmlu_college_physics": 0.0, "mmlu_computer_security": 0.0, "mmlu_conceptual_physics": 0.0, "mmlu_econometrics": 0.0, "mmlu_electrical_engineering": 0.0, "mmlu_elementary_mathematics": 0.0, "mmlu_formal_logic": 0.0, "mmlu_global_facts": 0.0, "mmlu_high_school_biology": 0.0, "mmlu_high_school_chemistry": 0.0, "mmlu_high_school_computer_science": 0.0, "mmlu_high_school_european_history": 0.0, "mmlu_high_school_geography": 0.0, "mmlu_high_school_government_and_politics": 0.0, "mmlu_high_school_macroeconomics": 0.0, "mmlu_high_school_mathematics": 0.0, "mmlu_high_school_microeconomics": 0.0, "mmlu_high_school_physics": 0.0, "mmlu_high_school_psychology": 0.0, "mmlu_high_school_statistics": 0.0, "mmlu_high_school_us_history": 0.0, "mmlu_high_school_world_history": 0.0, "mmlu_human_aging": 0.0, "mmlu_human_sexuality": 0.0, "mmlu_international_law": 0.0, "mmlu_jurisprudence": 0.0, "mmlu_logical_fallacies": 0.0, "mmlu_machine_learning": 0.0, "mmlu_management": 0.0, "mmlu_marketing": 0.0, "mmlu_medical_genetics": 0.0, "mmlu_miscellaneous": 0.0, "mmlu_moral_disputes": 0.0, "mmlu_moral_scenarios": 0.0, "mmlu_nutrition": 0.0, "mmlu_philosophy": 0.0, "mmlu_prehistory": 0.0, "mmlu_professional_accounting": 0.0, "mmlu_professional_law": 0.0, "mmlu_professional_medicine": 0.0, "mmlu_professional_psychology": 0.0, "mmlu_public_relations": 0.0, "mmlu_security_studies": 0.0, "mmlu_sociology": 0.0, "mmlu_us_foreign_policy": 0.0, "mmlu_virology": 0.0, "mmlu_world_religions": 0.0 }, "n-shot": { "mmlu": 0, "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_humanities": 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_other": 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_social_sciences": 5, "mmlu_sociology": 5, "mmlu_stem": 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_philosophy": { "original": 311, "effective": 311 }, "mmlu_logical_fallacies": { "original": 163, "effective": 163 }, "mmlu_moral_disputes": { "original": 346, "effective": 346 }, "mmlu_jurisprudence": { "original": 108, "effective": 108 }, "mmlu_high_school_us_history": { "original": 204, "effective": 204 }, "mmlu_high_school_world_history": { "original": 237, "effective": 237 }, "mmlu_world_religions": { "original": 171, "effective": 171 }, "mmlu_moral_scenarios": { "original": 895, "effective": 895 }, "mmlu_prehistory": { "original": 324, "effective": 324 }, "mmlu_formal_logic": { "original": 126, "effective": 126 }, "mmlu_international_law": { "original": 121, "effective": 121 }, "mmlu_professional_law": { "original": 1534, "effective": 1534 }, "mmlu_high_school_european_history": { "original": 165, "effective": 165 }, "mmlu_public_relations": { "original": 110, "effective": 110 }, "mmlu_high_school_macroeconomics": { "original": 390, "effective": 390 }, "mmlu_human_sexuality": { "original": 131, "effective": 131 }, "mmlu_high_school_geography": { "original": 198, "effective": 198 }, "mmlu_high_school_psychology": { "original": 545, "effective": 545 }, "mmlu_high_school_microeconomics": { "original": 238, "effective": 238 }, "mmlu_high_school_government_and_politics": { "original": 193, "effective": 193 }, "mmlu_us_foreign_policy": { "original": 100, "effective": 100 }, "mmlu_sociology": { "original": 201, "effective": 201 }, "mmlu_security_studies": { "original": 245, "effective": 245 }, "mmlu_econometrics": { "original": 114, "effective": 114 }, "mmlu_professional_psychology": { "original": 612, "effective": 612 }, "mmlu_business_ethics": { "original": 100, "effective": 100 }, "mmlu_marketing": { "original": 234, "effective": 234 }, "mmlu_medical_genetics": { "original": 100, "effective": 100 }, "mmlu_clinical_knowledge": { "original": 265, "effective": 265 }, "mmlu_global_facts": { "original": 100, "effective": 100 }, "mmlu_human_aging": { "original": 223, "effective": 223 }, "mmlu_professional_medicine": { "original": 272, "effective": 272 }, "mmlu_nutrition": { "original": 306, "effective": 306 }, "mmlu_management": { "original": 103, "effective": 103 }, "mmlu_college_medicine": { "original": 173, "effective": 173 }, "mmlu_professional_accounting": { "original": 282, "effective": 282 }, "mmlu_virology": { "original": 166, "effective": 166 }, "mmlu_miscellaneous": { "original": 783, "effective": 783 }, "mmlu_abstract_algebra": { "original": 100, "effective": 100 }, "mmlu_college_biology": { "original": 144, "effective": 144 }, "mmlu_high_school_biology": { "original": 310, "effective": 310 }, "mmlu_conceptual_physics": { "original": 235, "effective": 235 }, "mmlu_computer_security": { "original": 100, "effective": 100 }, "mmlu_college_physics": { "original": 102, "effective": 102 }, "mmlu_college_chemistry": { "original": 100, "effective": 100 }, "mmlu_high_school_statistics": { "original": 216, "effective": 216 }, "mmlu_anatomy": { "original": 135, "effective": 135 }, "mmlu_high_school_mathematics": { "original": 270, "effective": 270 }, "mmlu_machine_learning": { "original": 112, "effective": 112 }, "mmlu_high_school_physics": { "original": 151, "effective": 151 }, "mmlu_electrical_engineering": { "original": 145, "effective": 145 }, "mmlu_college_computer_science": { "original": 100, "effective": 100 }, "mmlu_high_school_chemistry": { "original": 203, "effective": 203 }, "mmlu_astronomy": { "original": 152, "effective": 152 }, "mmlu_high_school_computer_science": { "original": 100, "effective": 100 }, "mmlu_elementary_mathematics": { "original": 378, "effective": 378 }, "mmlu_college_mathematics": { "original": 100, "effective": 100 } }, "config": { "model": "vllm", "model_args": "pretrained=/cache/abhinav/models/Phase1/gptq-Qwen/Qwen2-1.5B-Instruct-garage-bAInd/Open-Platypus-mse-damp0.1-ns512-seqlen4K,tensor_parallel_size=2,dtype=auto,add_bos_token=True,gpu_memory_utilization=0.4,data_parallel_size=1,max_model_len=4096", "batch_size": "auto", "batch_sizes": [], "device": "cuda", "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": 1719624343.9120553, "pretty_env_info": "PyTorch version: 2.3.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.6\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-101-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 545.23.08\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\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 256\nOn-line CPU(s) list: 0-255\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7763 64-Core Processor\nCPU family: 25\nModel: 1\nThread(s) per core: 2\nCore(s) per socket: 64\nSocket(s): 2\nStepping: 1\nFrequency boost: enabled\nCPU max MHz: 3529.0520\nCPU min MHz: 1500.0000\nBogoMIPS: 4900.22\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm\nVirtualization: AMD-V\nL1d cache: 4 MiB (128 instances)\nL1i cache: 4 MiB (128 instances)\nL2 cache: 64 MiB (128 instances)\nL3 cache: 512 MiB (16 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-63,128-191\nNUMA node1 CPU(s): 64-127,192-255\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.3.0\n[pip3] triton==2.3.0\n[conda] Could not collect", "transformers_version": "4.41.2", "upper_git_hash": null, "task_hashes": {}, "model_source": "vllm", "model_name": "/cache/abhinav/models/Phase1/gptq-Qwen/Qwen2-1.5B-Instruct-garage-bAInd/Open-Platypus-mse-damp0.1-ns512-seqlen4K", "model_name_sanitized": "__cache__abhinav__models__Phase1__gptq-Qwen__Qwen2-1.5B-Instruct-garage-bAInd__Open-Platypus-mse-damp0.1-ns512-seqlen4K", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 7638031.049041288, "end_time": 7641735.991916678, "total_evaluation_time_seconds": "3704.942875389941" }