joermd's picture
Clone model from ALLaM-AI/ALLaM-7B-Instruct-preview
6f25beb verified
raw
history blame
104 kB
{
"results": {
"mmlu": {
"acc,none": 0.6813844181740493,
"acc_stderr,none": 0.0036893340664510663,
"alias": "mmlu"
},
"mmlu_humanities": {
"acc,none": 0.5989373007438895,
"acc_stderr,none": 0.006561339743251598,
"alias": " - humanities"
},
"mmlu_formal_logic": {
"alias": " - formal_logic",
"acc,none": 0.6031746031746031,
"acc_stderr,none": 0.0437588849272706
},
"mmlu_high_school_european_history": {
"alias": " - high_school_european_history",
"acc,none": 0.8,
"acc_stderr,none": 0.031234752377721175
},
"mmlu_high_school_us_history": {
"alias": " - high_school_us_history",
"acc,none": 0.8431372549019608,
"acc_stderr,none": 0.025524722324553332
},
"mmlu_high_school_world_history": {
"alias": " - high_school_world_history",
"acc,none": 0.8565400843881856,
"acc_stderr,none": 0.022818291821017012
},
"mmlu_international_law": {
"alias": " - international_law",
"acc,none": 0.8181818181818182,
"acc_stderr,none": 0.03520893951097654
},
"mmlu_jurisprudence": {
"alias": " - jurisprudence",
"acc,none": 0.7962962962962963,
"acc_stderr,none": 0.03893542518824849
},
"mmlu_logical_fallacies": {
"alias": " - logical_fallacies",
"acc,none": 0.7852760736196319,
"acc_stderr,none": 0.032262193772867744
},
"mmlu_moral_disputes": {
"alias": " - moral_disputes",
"acc,none": 0.7398843930635838,
"acc_stderr,none": 0.023618678310069363
},
"mmlu_moral_scenarios": {
"alias": " - moral_scenarios",
"acc,none": 0.2905027932960894,
"acc_stderr,none": 0.015183844307206155
},
"mmlu_philosophy": {
"alias": " - philosophy",
"acc,none": 0.7684887459807074,
"acc_stderr,none": 0.023956532766639137
},
"mmlu_prehistory": {
"alias": " - prehistory",
"acc,none": 0.7530864197530864,
"acc_stderr,none": 0.023993501709042117
},
"mmlu_professional_law": {
"alias": " - professional_law",
"acc,none": 0.5097783572359843,
"acc_stderr,none": 0.012767793787729338
},
"mmlu_world_religions": {
"alias": " - world_religions",
"acc,none": 0.8245614035087719,
"acc_stderr,none": 0.02917088550072766
},
"mmlu_other": {
"acc,none": 0.7219182491149019,
"acc_stderr,none": 0.007753178518309848,
"alias": " - other"
},
"mmlu_business_ethics": {
"alias": " - business_ethics",
"acc,none": 0.67,
"acc_stderr,none": 0.04725815626252609
},
"mmlu_clinical_knowledge": {
"alias": " - clinical_knowledge",
"acc,none": 0.7283018867924528,
"acc_stderr,none": 0.027377706624670713
},
"mmlu_college_medicine": {
"alias": " - college_medicine",
"acc,none": 0.6473988439306358,
"acc_stderr,none": 0.036430371689585496
},
"mmlu_global_facts": {
"alias": " - global_facts",
"acc,none": 0.4,
"acc_stderr,none": 0.049236596391733084
},
"mmlu_human_aging": {
"alias": " - human_aging",
"acc,none": 0.7309417040358744,
"acc_stderr,none": 0.02976377940687497
},
"mmlu_management": {
"alias": " - management",
"acc,none": 0.8252427184466019,
"acc_stderr,none": 0.037601780060266196
},
"mmlu_marketing": {
"alias": " - marketing",
"acc,none": 0.8974358974358975,
"acc_stderr,none": 0.01987565502786744
},
"mmlu_medical_genetics": {
"alias": " - medical_genetics",
"acc,none": 0.77,
"acc_stderr,none": 0.04229525846816502
},
"mmlu_miscellaneous": {
"alias": " - miscellaneous",
"acc,none": 0.8237547892720306,
"acc_stderr,none": 0.01362555690799346
},
"mmlu_nutrition": {
"alias": " - nutrition",
"acc,none": 0.7287581699346405,
"acc_stderr,none": 0.025457756696667864
},
"mmlu_professional_accounting": {
"alias": " - professional_accounting",
"acc,none": 0.5354609929078015,
"acc_stderr,none": 0.02975238965742705
},
"mmlu_professional_medicine": {
"alias": " - professional_medicine",
"acc,none": 0.7095588235294118,
"acc_stderr,none": 0.02757646862274052
},
"mmlu_virology": {
"alias": " - virology",
"acc,none": 0.5060240963855421,
"acc_stderr,none": 0.03892212195333045
},
"mmlu_social_sciences": {
"acc,none": 0.785830354241144,
"acc_stderr,none": 0.007242767358068179,
"alias": " - social sciences"
},
"mmlu_econometrics": {
"alias": " - econometrics",
"acc,none": 0.5964912280701754,
"acc_stderr,none": 0.046151869625837054
},
"mmlu_high_school_geography": {
"alias": " - high_school_geography",
"acc,none": 0.8181818181818182,
"acc_stderr,none": 0.0274796030105388
},
"mmlu_high_school_government_and_politics": {
"alias": " - high_school_government_and_politics",
"acc,none": 0.8911917098445595,
"acc_stderr,none": 0.022473253332768766
},
"mmlu_high_school_macroeconomics": {
"alias": " - high_school_macroeconomics",
"acc,none": 0.7307692307692307,
"acc_stderr,none": 0.022489389793654824
},
"mmlu_high_school_microeconomics": {
"alias": " - high_school_microeconomics",
"acc,none": 0.8865546218487395,
"acc_stderr,none": 0.02060022575020482
},
"mmlu_high_school_psychology": {
"alias": " - high_school_psychology",
"acc,none": 0.8844036697247707,
"acc_stderr,none": 0.01370874953417264
},
"mmlu_human_sexuality": {
"alias": " - human_sexuality",
"acc,none": 0.7633587786259542,
"acc_stderr,none": 0.03727673575596915
},
"mmlu_professional_psychology": {
"alias": " - professional_psychology",
"acc,none": 0.7124183006535948,
"acc_stderr,none": 0.018311653053648222
},
"mmlu_public_relations": {
"alias": " - public_relations",
"acc,none": 0.6454545454545455,
"acc_stderr,none": 0.04582004841505415
},
"mmlu_security_studies": {
"alias": " - security_studies",
"acc,none": 0.7183673469387755,
"acc_stderr,none": 0.02879518557429129
},
"mmlu_sociology": {
"alias": " - sociology",
"acc,none": 0.8407960199004975,
"acc_stderr,none": 0.02587064676616914
},
"mmlu_us_foreign_policy": {
"alias": " - us_foreign_policy",
"acc,none": 0.86,
"acc_stderr,none": 0.03487350880197768
},
"mmlu_stem": {
"acc,none": 0.6625436092610213,
"acc_stderr,none": 0.008110145398407284,
"alias": " - stem"
},
"mmlu_abstract_algebra": {
"alias": " - abstract_algebra",
"acc,none": 0.49,
"acc_stderr,none": 0.05024183937956911
},
"mmlu_anatomy": {
"alias": " - anatomy",
"acc,none": 0.6222222222222222,
"acc_stderr,none": 0.04188307537595853
},
"mmlu_astronomy": {
"alias": " - astronomy",
"acc,none": 0.8026315789473685,
"acc_stderr,none": 0.03238981601699397
},
"mmlu_college_biology": {
"alias": " - college_biology",
"acc,none": 0.8402777777777778,
"acc_stderr,none": 0.030635578972093274
},
"mmlu_college_chemistry": {
"alias": " - college_chemistry",
"acc,none": 0.54,
"acc_stderr,none": 0.05009082659620333
},
"mmlu_college_computer_science": {
"alias": " - college_computer_science",
"acc,none": 0.69,
"acc_stderr,none": 0.04648231987117316
},
"mmlu_college_mathematics": {
"alias": " - college_mathematics",
"acc,none": 0.47,
"acc_stderr,none": 0.05016135580465919
},
"mmlu_college_physics": {
"alias": " - college_physics",
"acc,none": 0.5196078431372549,
"acc_stderr,none": 0.04971358884367405
},
"mmlu_computer_security": {
"alias": " - computer_security",
"acc,none": 0.79,
"acc_stderr,none": 0.040936018074033256
},
"mmlu_conceptual_physics": {
"alias": " - conceptual_physics",
"acc,none": 0.7617021276595745,
"acc_stderr,none": 0.027851252973889788
},
"mmlu_electrical_engineering": {
"alias": " - electrical_engineering",
"acc,none": 0.7379310344827587,
"acc_stderr,none": 0.036646663372252565
},
"mmlu_elementary_mathematics": {
"alias": " - elementary_mathematics",
"acc,none": 0.6402116402116402,
"acc_stderr,none": 0.024718075944129274
},
"mmlu_high_school_biology": {
"alias": " - high_school_biology",
"acc,none": 0.8419354838709677,
"acc_stderr,none": 0.02075283151187526
},
"mmlu_high_school_chemistry": {
"alias": " - high_school_chemistry",
"acc,none": 0.6206896551724138,
"acc_stderr,none": 0.03413963805906235
},
"mmlu_high_school_computer_science": {
"alias": " - high_school_computer_science",
"acc,none": 0.81,
"acc_stderr,none": 0.03942772444036623
},
"mmlu_high_school_mathematics": {
"alias": " - high_school_mathematics",
"acc,none": 0.4,
"acc_stderr,none": 0.02986960509531691
},
"mmlu_high_school_physics": {
"alias": " - high_school_physics",
"acc,none": 0.6423841059602649,
"acc_stderr,none": 0.03913453431177258
},
"mmlu_high_school_statistics": {
"alias": " - high_school_statistics",
"acc,none": 0.6712962962962963,
"acc_stderr,none": 0.03203614084670058
},
"mmlu_machine_learning": {
"alias": " - machine_learning",
"acc,none": 0.5803571428571429,
"acc_stderr,none": 0.046840993210771065
}
},
"groups": {
"mmlu": {
"acc,none": 0.6813844181740493,
"acc_stderr,none": 0.0036893340664510663,
"alias": "mmlu"
},
"mmlu_humanities": {
"acc,none": 0.5989373007438895,
"acc_stderr,none": 0.006561339743251598,
"alias": " - humanities"
},
"mmlu_other": {
"acc,none": 0.7219182491149019,
"acc_stderr,none": 0.007753178518309848,
"alias": " - other"
},
"mmlu_social_sciences": {
"acc,none": 0.785830354241144,
"acc_stderr,none": 0.007242767358068179,
"alias": " - social sciences"
},
"mmlu_stem": {
"acc,none": 0.6625436092610213,
"acc_stderr,none": 0.008110145398407284,
"alias": " - stem"
}
},
"group_subtasks": {
"mmlu_humanities": [
"mmlu_jurisprudence",
"mmlu_international_law",
"mmlu_moral_scenarios",
"mmlu_philosophy",
"mmlu_high_school_world_history",
"mmlu_formal_logic",
"mmlu_high_school_us_history",
"mmlu_moral_disputes",
"mmlu_logical_fallacies",
"mmlu_high_school_european_history",
"mmlu_world_religions",
"mmlu_prehistory",
"mmlu_professional_law"
],
"mmlu_social_sciences": [
"mmlu_human_sexuality",
"mmlu_high_school_psychology",
"mmlu_us_foreign_policy",
"mmlu_professional_psychology",
"mmlu_econometrics",
"mmlu_public_relations",
"mmlu_high_school_macroeconomics",
"mmlu_high_school_geography",
"mmlu_sociology",
"mmlu_high_school_government_and_politics",
"mmlu_security_studies",
"mmlu_high_school_microeconomics"
],
"mmlu_other": [
"mmlu_miscellaneous",
"mmlu_professional_medicine",
"mmlu_marketing",
"mmlu_business_ethics",
"mmlu_clinical_knowledge",
"mmlu_human_aging",
"mmlu_professional_accounting",
"mmlu_medical_genetics",
"mmlu_college_medicine",
"mmlu_virology",
"mmlu_nutrition",
"mmlu_management",
"mmlu_global_facts"
],
"mmlu_stem": [
"mmlu_elementary_mathematics",
"mmlu_electrical_engineering",
"mmlu_college_mathematics",
"mmlu_machine_learning",
"mmlu_high_school_physics",
"mmlu_high_school_biology",
"mmlu_abstract_algebra",
"mmlu_college_biology",
"mmlu_college_physics",
"mmlu_computer_security",
"mmlu_college_computer_science",
"mmlu_high_school_chemistry",
"mmlu_high_school_computer_science",
"mmlu_conceptual_physics",
"mmlu_high_school_statistics",
"mmlu_college_chemistry",
"mmlu_astronomy",
"mmlu_anatomy",
"mmlu_high_school_mathematics"
],
"mmlu": [
"mmlu_stem",
"mmlu_other",
"mmlu_social_sciences",
"mmlu_humanities"
]
},
"configs": {
"mmlu_abstract_algebra": {
"task": "mmlu_abstract_algebra",
"task_alias": "abstract_algebra",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "abstract_algebra",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_anatomy": {
"task": "mmlu_anatomy",
"task_alias": "anatomy",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "anatomy",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about anatomy.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_astronomy": {
"task": "mmlu_astronomy",
"task_alias": "astronomy",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "astronomy",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about astronomy.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_business_ethics": {
"task": "mmlu_business_ethics",
"task_alias": "business_ethics",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "business_ethics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about business ethics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_clinical_knowledge": {
"task": "mmlu_clinical_knowledge",
"task_alias": "clinical_knowledge",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "clinical_knowledge",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_college_biology": {
"task": "mmlu_college_biology",
"task_alias": "college_biology",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "college_biology",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about college biology.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_college_chemistry": {
"task": "mmlu_college_chemistry",
"task_alias": "college_chemistry",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "college_chemistry",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about college chemistry.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_college_computer_science": {
"task": "mmlu_college_computer_science",
"task_alias": "college_computer_science",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "college_computer_science",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about college computer science.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_college_mathematics": {
"task": "mmlu_college_mathematics",
"task_alias": "college_mathematics",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "college_mathematics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about college mathematics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_college_medicine": {
"task": "mmlu_college_medicine",
"task_alias": "college_medicine",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "college_medicine",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about college medicine.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_college_physics": {
"task": "mmlu_college_physics",
"task_alias": "college_physics",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "college_physics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about college physics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_computer_security": {
"task": "mmlu_computer_security",
"task_alias": "computer_security",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "computer_security",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about computer security.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_conceptual_physics": {
"task": "mmlu_conceptual_physics",
"task_alias": "conceptual_physics",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "conceptual_physics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_econometrics": {
"task": "mmlu_econometrics",
"task_alias": "econometrics",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "econometrics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about econometrics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_electrical_engineering": {
"task": "mmlu_electrical_engineering",
"task_alias": "electrical_engineering",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "electrical_engineering",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_elementary_mathematics": {
"task": "mmlu_elementary_mathematics",
"task_alias": "elementary_mathematics",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "elementary_mathematics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_formal_logic": {
"task": "mmlu_formal_logic",
"task_alias": "formal_logic",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "formal_logic",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about formal logic.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_global_facts": {
"task": "mmlu_global_facts",
"task_alias": "global_facts",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "global_facts",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about global facts.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_biology": {
"task": "mmlu_high_school_biology",
"task_alias": "high_school_biology",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_biology",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school biology.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_chemistry": {
"task": "mmlu_high_school_chemistry",
"task_alias": "high_school_chemistry",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_chemistry",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_computer_science": {
"task": "mmlu_high_school_computer_science",
"task_alias": "high_school_computer_science",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_computer_science",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school computer science.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_european_history": {
"task": "mmlu_high_school_european_history",
"task_alias": "high_school_european_history",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_european_history",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school european history.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_geography": {
"task": "mmlu_high_school_geography",
"task_alias": "high_school_geography",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_geography",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school geography.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_government_and_politics": {
"task": "mmlu_high_school_government_and_politics",
"task_alias": "high_school_government_and_politics",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_government_and_politics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_macroeconomics": {
"task": "mmlu_high_school_macroeconomics",
"task_alias": "high_school_macroeconomics",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_macroeconomics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_mathematics": {
"task": "mmlu_high_school_mathematics",
"task_alias": "high_school_mathematics",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_mathematics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_microeconomics": {
"task": "mmlu_high_school_microeconomics",
"task_alias": "high_school_microeconomics",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_microeconomics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_physics": {
"task": "mmlu_high_school_physics",
"task_alias": "high_school_physics",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_physics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school physics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_psychology": {
"task": "mmlu_high_school_psychology",
"task_alias": "high_school_psychology",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_psychology",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school psychology.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_statistics": {
"task": "mmlu_high_school_statistics",
"task_alias": "high_school_statistics",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_statistics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school statistics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_us_history": {
"task": "mmlu_high_school_us_history",
"task_alias": "high_school_us_history",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_us_history",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school us history.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_high_school_world_history": {
"task": "mmlu_high_school_world_history",
"task_alias": "high_school_world_history",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "high_school_world_history",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about high school world history.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_human_aging": {
"task": "mmlu_human_aging",
"task_alias": "human_aging",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "human_aging",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about human aging.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_human_sexuality": {
"task": "mmlu_human_sexuality",
"task_alias": "human_sexuality",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "human_sexuality",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about human sexuality.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_international_law": {
"task": "mmlu_international_law",
"task_alias": "international_law",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "international_law",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about international law.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_jurisprudence": {
"task": "mmlu_jurisprudence",
"task_alias": "jurisprudence",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "jurisprudence",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_logical_fallacies": {
"task": "mmlu_logical_fallacies",
"task_alias": "logical_fallacies",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "logical_fallacies",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_machine_learning": {
"task": "mmlu_machine_learning",
"task_alias": "machine_learning",
"tag": "mmlu_stem_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "machine_learning",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about machine learning.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_management": {
"task": "mmlu_management",
"task_alias": "management",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "management",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about management.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_marketing": {
"task": "mmlu_marketing",
"task_alias": "marketing",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "marketing",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about marketing.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_medical_genetics": {
"task": "mmlu_medical_genetics",
"task_alias": "medical_genetics",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "medical_genetics",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about medical genetics.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_miscellaneous": {
"task": "mmlu_miscellaneous",
"task_alias": "miscellaneous",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "miscellaneous",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_moral_disputes": {
"task": "mmlu_moral_disputes",
"task_alias": "moral_disputes",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "moral_disputes",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about moral disputes.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_moral_scenarios": {
"task": "mmlu_moral_scenarios",
"task_alias": "moral_scenarios",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "moral_scenarios",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_nutrition": {
"task": "mmlu_nutrition",
"task_alias": "nutrition",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "nutrition",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about nutrition.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_philosophy": {
"task": "mmlu_philosophy",
"task_alias": "philosophy",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "philosophy",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about philosophy.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_prehistory": {
"task": "mmlu_prehistory",
"task_alias": "prehistory",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "prehistory",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about prehistory.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_professional_accounting": {
"task": "mmlu_professional_accounting",
"task_alias": "professional_accounting",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "professional_accounting",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about professional accounting.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_professional_law": {
"task": "mmlu_professional_law",
"task_alias": "professional_law",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "professional_law",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about professional law.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_professional_medicine": {
"task": "mmlu_professional_medicine",
"task_alias": "professional_medicine",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "professional_medicine",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about professional medicine.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_professional_psychology": {
"task": "mmlu_professional_psychology",
"task_alias": "professional_psychology",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "professional_psychology",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about professional psychology.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_public_relations": {
"task": "mmlu_public_relations",
"task_alias": "public_relations",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "public_relations",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about public relations.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_security_studies": {
"task": "mmlu_security_studies",
"task_alias": "security_studies",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "security_studies",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about security studies.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_sociology": {
"task": "mmlu_sociology",
"task_alias": "sociology",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "sociology",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about sociology.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_us_foreign_policy": {
"task": "mmlu_us_foreign_policy",
"task_alias": "us_foreign_policy",
"tag": "mmlu_social_sciences_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "us_foreign_policy",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about us foreign policy.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_virology": {
"task": "mmlu_virology",
"task_alias": "virology",
"tag": "mmlu_other_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "virology",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about virology.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"mmlu_world_religions": {
"task": "mmlu_world_religions",
"task_alias": "world_religions",
"tag": "mmlu_humanities_tasks",
"dataset_path": "hails/mmlu_no_train",
"dataset_name": "world_religions",
"dataset_kwargs": {
"trust_remote_code": true
},
"test_split": "test",
"fewshot_split": "dev",
"doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
"doc_to_target": "answer",
"doc_to_choice": [
"A",
"B",
"C",
"D"
],
"description": "The following are multiple choice questions (with answers) about world religions.\n\n",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "first_n"
},
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
}
},
"versions": {
"mmlu": 2,
"mmlu_abstract_algebra": 1.0,
"mmlu_anatomy": 1.0,
"mmlu_astronomy": 1.0,
"mmlu_business_ethics": 1.0,
"mmlu_clinical_knowledge": 1.0,
"mmlu_college_biology": 1.0,
"mmlu_college_chemistry": 1.0,
"mmlu_college_computer_science": 1.0,
"mmlu_college_mathematics": 1.0,
"mmlu_college_medicine": 1.0,
"mmlu_college_physics": 1.0,
"mmlu_computer_security": 1.0,
"mmlu_conceptual_physics": 1.0,
"mmlu_econometrics": 1.0,
"mmlu_electrical_engineering": 1.0,
"mmlu_elementary_mathematics": 1.0,
"mmlu_formal_logic": 1.0,
"mmlu_global_facts": 1.0,
"mmlu_high_school_biology": 1.0,
"mmlu_high_school_chemistry": 1.0,
"mmlu_high_school_computer_science": 1.0,
"mmlu_high_school_european_history": 1.0,
"mmlu_high_school_geography": 1.0,
"mmlu_high_school_government_and_politics": 1.0,
"mmlu_high_school_macroeconomics": 1.0,
"mmlu_high_school_mathematics": 1.0,
"mmlu_high_school_microeconomics": 1.0,
"mmlu_high_school_physics": 1.0,
"mmlu_high_school_psychology": 1.0,
"mmlu_high_school_statistics": 1.0,
"mmlu_high_school_us_history": 1.0,
"mmlu_high_school_world_history": 1.0,
"mmlu_human_aging": 1.0,
"mmlu_human_sexuality": 1.0,
"mmlu_humanities": 2,
"mmlu_international_law": 1.0,
"mmlu_jurisprudence": 1.0,
"mmlu_logical_fallacies": 1.0,
"mmlu_machine_learning": 1.0,
"mmlu_management": 1.0,
"mmlu_marketing": 1.0,
"mmlu_medical_genetics": 1.0,
"mmlu_miscellaneous": 1.0,
"mmlu_moral_disputes": 1.0,
"mmlu_moral_scenarios": 1.0,
"mmlu_nutrition": 1.0,
"mmlu_other": 2,
"mmlu_philosophy": 1.0,
"mmlu_prehistory": 1.0,
"mmlu_professional_accounting": 1.0,
"mmlu_professional_law": 1.0,
"mmlu_professional_medicine": 1.0,
"mmlu_professional_psychology": 1.0,
"mmlu_public_relations": 1.0,
"mmlu_security_studies": 1.0,
"mmlu_social_sciences": 2,
"mmlu_sociology": 1.0,
"mmlu_stem": 2,
"mmlu_us_foreign_policy": 1.0,
"mmlu_virology": 1.0,
"mmlu_world_religions": 1.0
},
"n-shot": {
"mmlu_abstract_algebra": 0,
"mmlu_anatomy": 0,
"mmlu_astronomy": 0,
"mmlu_business_ethics": 0,
"mmlu_clinical_knowledge": 0,
"mmlu_college_biology": 0,
"mmlu_college_chemistry": 0,
"mmlu_college_computer_science": 0,
"mmlu_college_mathematics": 0,
"mmlu_college_medicine": 0,
"mmlu_college_physics": 0,
"mmlu_computer_security": 0,
"mmlu_conceptual_physics": 0,
"mmlu_econometrics": 0,
"mmlu_electrical_engineering": 0,
"mmlu_elementary_mathematics": 0,
"mmlu_formal_logic": 0,
"mmlu_global_facts": 0,
"mmlu_high_school_biology": 0,
"mmlu_high_school_chemistry": 0,
"mmlu_high_school_computer_science": 0,
"mmlu_high_school_european_history": 0,
"mmlu_high_school_geography": 0,
"mmlu_high_school_government_and_politics": 0,
"mmlu_high_school_macroeconomics": 0,
"mmlu_high_school_mathematics": 0,
"mmlu_high_school_microeconomics": 0,
"mmlu_high_school_physics": 0,
"mmlu_high_school_psychology": 0,
"mmlu_high_school_statistics": 0,
"mmlu_high_school_us_history": 0,
"mmlu_high_school_world_history": 0,
"mmlu_human_aging": 0,
"mmlu_human_sexuality": 0,
"mmlu_international_law": 0,
"mmlu_jurisprudence": 0,
"mmlu_logical_fallacies": 0,
"mmlu_machine_learning": 0,
"mmlu_management": 0,
"mmlu_marketing": 0,
"mmlu_medical_genetics": 0,
"mmlu_miscellaneous": 0,
"mmlu_moral_disputes": 0,
"mmlu_moral_scenarios": 0,
"mmlu_nutrition": 0,
"mmlu_philosophy": 0,
"mmlu_prehistory": 0,
"mmlu_professional_accounting": 0,
"mmlu_professional_law": 0,
"mmlu_professional_medicine": 0,
"mmlu_professional_psychology": 0,
"mmlu_public_relations": 0,
"mmlu_security_studies": 0,
"mmlu_sociology": 0,
"mmlu_us_foreign_policy": 0,
"mmlu_virology": 0,
"mmlu_world_religions": 0
},
"higher_is_better": {
"mmlu": {
"acc": true
},
"mmlu_abstract_algebra": {
"acc": true
},
"mmlu_anatomy": {
"acc": true
},
"mmlu_astronomy": {
"acc": true
},
"mmlu_business_ethics": {
"acc": true
},
"mmlu_clinical_knowledge": {
"acc": true
},
"mmlu_college_biology": {
"acc": true
},
"mmlu_college_chemistry": {
"acc": true
},
"mmlu_college_computer_science": {
"acc": true
},
"mmlu_college_mathematics": {
"acc": true
},
"mmlu_college_medicine": {
"acc": true
},
"mmlu_college_physics": {
"acc": true
},
"mmlu_computer_security": {
"acc": true
},
"mmlu_conceptual_physics": {
"acc": true
},
"mmlu_econometrics": {
"acc": true
},
"mmlu_electrical_engineering": {
"acc": true
},
"mmlu_elementary_mathematics": {
"acc": true
},
"mmlu_formal_logic": {
"acc": true
},
"mmlu_global_facts": {
"acc": true
},
"mmlu_high_school_biology": {
"acc": true
},
"mmlu_high_school_chemistry": {
"acc": true
},
"mmlu_high_school_computer_science": {
"acc": true
},
"mmlu_high_school_european_history": {
"acc": true
},
"mmlu_high_school_geography": {
"acc": true
},
"mmlu_high_school_government_and_politics": {
"acc": true
},
"mmlu_high_school_macroeconomics": {
"acc": true
},
"mmlu_high_school_mathematics": {
"acc": true
},
"mmlu_high_school_microeconomics": {
"acc": true
},
"mmlu_high_school_physics": {
"acc": true
},
"mmlu_high_school_psychology": {
"acc": true
},
"mmlu_high_school_statistics": {
"acc": true
},
"mmlu_high_school_us_history": {
"acc": true
},
"mmlu_high_school_world_history": {
"acc": true
},
"mmlu_human_aging": {
"acc": true
},
"mmlu_human_sexuality": {
"acc": true
},
"mmlu_humanities": {
"acc": true
},
"mmlu_international_law": {
"acc": true
},
"mmlu_jurisprudence": {
"acc": true
},
"mmlu_logical_fallacies": {
"acc": true
},
"mmlu_machine_learning": {
"acc": true
},
"mmlu_management": {
"acc": true
},
"mmlu_marketing": {
"acc": true
},
"mmlu_medical_genetics": {
"acc": true
},
"mmlu_miscellaneous": {
"acc": true
},
"mmlu_moral_disputes": {
"acc": true
},
"mmlu_moral_scenarios": {
"acc": true
},
"mmlu_nutrition": {
"acc": true
},
"mmlu_other": {
"acc": true
},
"mmlu_philosophy": {
"acc": true
},
"mmlu_prehistory": {
"acc": true
},
"mmlu_professional_accounting": {
"acc": true
},
"mmlu_professional_law": {
"acc": true
},
"mmlu_professional_medicine": {
"acc": true
},
"mmlu_professional_psychology": {
"acc": true
},
"mmlu_public_relations": {
"acc": true
},
"mmlu_security_studies": {
"acc": true
},
"mmlu_social_sciences": {
"acc": true
},
"mmlu_sociology": {
"acc": true
},
"mmlu_stem": {
"acc": true
},
"mmlu_us_foreign_policy": {
"acc": true
},
"mmlu_virology": {
"acc": true
},
"mmlu_world_religions": {
"acc": true
}
},
"n-samples": {
"mmlu_elementary_mathematics": {
"original": 378,
"effective": 378
},
"mmlu_electrical_engineering": {
"original": 145,
"effective": 145
},
"mmlu_college_mathematics": {
"original": 100,
"effective": 100
},
"mmlu_machine_learning": {
"original": 112,
"effective": 112
},
"mmlu_high_school_physics": {
"original": 151,
"effective": 151
},
"mmlu_high_school_biology": {
"original": 310,
"effective": 310
},
"mmlu_abstract_algebra": {
"original": 100,
"effective": 100
},
"mmlu_college_biology": {
"original": 144,
"effective": 144
},
"mmlu_college_physics": {
"original": 102,
"effective": 102
},
"mmlu_computer_security": {
"original": 100,
"effective": 100
},
"mmlu_college_computer_science": {
"original": 100,
"effective": 100
},
"mmlu_high_school_chemistry": {
"original": 203,
"effective": 203
},
"mmlu_high_school_computer_science": {
"original": 100,
"effective": 100
},
"mmlu_conceptual_physics": {
"original": 235,
"effective": 235
},
"mmlu_high_school_statistics": {
"original": 216,
"effective": 216
},
"mmlu_college_chemistry": {
"original": 100,
"effective": 100
},
"mmlu_astronomy": {
"original": 152,
"effective": 152
},
"mmlu_anatomy": {
"original": 135,
"effective": 135
},
"mmlu_high_school_mathematics": {
"original": 270,
"effective": 270
},
"mmlu_miscellaneous": {
"original": 783,
"effective": 783
},
"mmlu_professional_medicine": {
"original": 272,
"effective": 272
},
"mmlu_marketing": {
"original": 234,
"effective": 234
},
"mmlu_business_ethics": {
"original": 100,
"effective": 100
},
"mmlu_clinical_knowledge": {
"original": 265,
"effective": 265
},
"mmlu_human_aging": {
"original": 223,
"effective": 223
},
"mmlu_professional_accounting": {
"original": 282,
"effective": 282
},
"mmlu_medical_genetics": {
"original": 100,
"effective": 100
},
"mmlu_college_medicine": {
"original": 173,
"effective": 173
},
"mmlu_virology": {
"original": 166,
"effective": 166
},
"mmlu_nutrition": {
"original": 306,
"effective": 306
},
"mmlu_management": {
"original": 103,
"effective": 103
},
"mmlu_global_facts": {
"original": 100,
"effective": 100
},
"mmlu_human_sexuality": {
"original": 131,
"effective": 131
},
"mmlu_high_school_psychology": {
"original": 545,
"effective": 545
},
"mmlu_us_foreign_policy": {
"original": 100,
"effective": 100
},
"mmlu_professional_psychology": {
"original": 612,
"effective": 612
},
"mmlu_econometrics": {
"original": 114,
"effective": 114
},
"mmlu_public_relations": {
"original": 110,
"effective": 110
},
"mmlu_high_school_macroeconomics": {
"original": 390,
"effective": 390
},
"mmlu_high_school_geography": {
"original": 198,
"effective": 198
},
"mmlu_sociology": {
"original": 201,
"effective": 201
},
"mmlu_high_school_government_and_politics": {
"original": 193,
"effective": 193
},
"mmlu_security_studies": {
"original": 245,
"effective": 245
},
"mmlu_high_school_microeconomics": {
"original": 238,
"effective": 238
},
"mmlu_jurisprudence": {
"original": 108,
"effective": 108
},
"mmlu_international_law": {
"original": 121,
"effective": 121
},
"mmlu_moral_scenarios": {
"original": 895,
"effective": 895
},
"mmlu_philosophy": {
"original": 311,
"effective": 311
},
"mmlu_high_school_world_history": {
"original": 237,
"effective": 237
},
"mmlu_formal_logic": {
"original": 126,
"effective": 126
},
"mmlu_high_school_us_history": {
"original": 204,
"effective": 204
},
"mmlu_moral_disputes": {
"original": 346,
"effective": 346
},
"mmlu_logical_fallacies": {
"original": 163,
"effective": 163
},
"mmlu_high_school_european_history": {
"original": 165,
"effective": 165
},
"mmlu_world_religions": {
"original": 171,
"effective": 171
},
"mmlu_prehistory": {
"original": 324,
"effective": 324
},
"mmlu_professional_law": {
"original": 1534,
"effective": 1534
}
},
"config": {
"model": "hf",
"model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True",
"model_num_parameters": 7455550464,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6",
"batch_size": 1,
"batch_sizes": [],
"device": null,
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000,
"gen_kwargs": null,
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": "5e10e017",
"date": 1736901843.8252811,
"pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
"transformers_version": "4.48.0",
"upper_git_hash": "f64fe2f2a86055aaecced603b56097fd79201711",
"tokenizer_pad_token": [
"<|pad|>",
"2023"
],
"tokenizer_eos_token": [
"<|endoftext|>",
"11"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 11,
"max_length": 32768,
"task_hashes": {
"mmlu_elementary_mathematics": "6d47e01621b1ff088cf4d2606be08a46ae4fa10d2bf3529bd5a0f85d2832e0f6",
"mmlu_electrical_engineering": "ef25c57c137bd2074c388edf889ea1a658e5a3afd3921887a6bdbe8b1cbdfc0f",
"mmlu_college_mathematics": "118ed98b6c4bd806f93efddf09a3041a5128e8d4582b9fb7fe12f1a1ae38ecf4",
"mmlu_machine_learning": "edba86c924c71abf5cc3c004d972c140f22bfabaa70041d3b8ae287866a9ce49",
"mmlu_high_school_physics": "51bae6e0d59010099d6b490c5740b24713b5e66662e552aa4698a662bbf8b628",
"mmlu_high_school_biology": "d99da3dd9a02094ae6e812eb30893f1b56ee748bf2ce91769728790f49a526b6",
"mmlu_abstract_algebra": "c63adb6be5bfb9380a7f822a05102e469983e4522ce2fccfb05dc3ebb618c36c",
"mmlu_college_biology": "ed93aba6c7bd7762a8eec5ce4b23c31549e52ced85fa75024d5996542518961b",
"mmlu_college_physics": "2cd501daecd35dbcfb2d3338cf04960dfdb8789384b7af321ddf480a4bb293e3",
"mmlu_computer_security": "adb17543d486c98e2c258c0b6450cf80889cfecbb204c658a88c375408a2d5ec",
"mmlu_college_computer_science": "eef39460f59676420a6cd82b21f0a338b0afbc17f6759e2e6ee9164ba6dda170",
"mmlu_high_school_chemistry": "6a0d95898c301509675c6c09024f1cfa75dfb7dd9c15709dc35428923b87c454",
"mmlu_high_school_computer_science": "005460140c49df97c405dee883789e0fc8e2747ce74f7eacd692e429e732b0b5",
"mmlu_conceptual_physics": "5eb25b75add800a0b85e7b69406dee40f20de3cd9f29c09fa65d59768449b729",
"mmlu_high_school_statistics": "7600e8753249d21170484a51da34e671ff61d837a4f4b7b92e763f04c178b4ba",
"mmlu_college_chemistry": "4793edf2d734030e6b49c443a4cfda8d2f2e34c9baa9112b9adb1cf79ba58bcf",
"mmlu_astronomy": "bb5d9f011ccdeeb9e89210e2c88fb2702d535c896dc8a544534ce19a77bdd40c",
"mmlu_anatomy": "f168b80d22fd964a0ea802808d94cdbf5cae82224e3d3602cc5ff912c366e1b3",
"mmlu_high_school_mathematics": "321f1383949b54f2f51402b09925541b2e8a171359ad8fb0433c5d99b9674595",
"mmlu_miscellaneous": "4c6d23e098aad1d79cdc6d956b8d66c3ca00003de07bd75300b870e9bf2ee253",
"mmlu_professional_medicine": "56b70c1334dacf62b62d5a21f32d30c640a6afb1522994c2884b411f6c4a9a0b",
"mmlu_marketing": "0134f11131a3a629c50102643862ebdd6acb617752938261b903ddb8afc40eba",
"mmlu_business_ethics": "3e5ad06da30b6bb600036f7ff0202a5a2d06c0803223dcf8873f5f5782892f7d",
"mmlu_clinical_knowledge": "3706b2cfd1a90b62b864d1534911d194afc384afb660563879d79e184e8cf3d4",
"mmlu_human_aging": "e97889b26bd5d7b0a80e0d167ca12b7ae771d6b7359f6d780fa7fd98f4dadcec",
"mmlu_professional_accounting": "7b38be5f62b6529524748f3a418444f8eaf77f17dcf40ed03a448118ec8b0f8f",
"mmlu_medical_genetics": "e2ba83d6fbd06d87b8311a7dff3b336a6c89c3686652b3932c7ab46b384552e0",
"mmlu_college_medicine": "971339e961cc8efc075c31d29cbc8f1a9834586160b0c5f46ff8b276afd0eec2",
"mmlu_virology": "58b8f73b5103985889402935e2b0ffbf1a11b295b801d07c44ee752350de5d99",
"mmlu_nutrition": "c6001266b538b2cdf473e816a2bcfeba547f03782c5bb0ad8804a2e1f97ea101",
"mmlu_management": "22ca56010a69657348db8209d89abbbd12516ce3d196999d223a5ec0f0a5fa8d",
"mmlu_global_facts": "0fecc8ba2c707eb82bbcbc7c59231aa56bf199d6241ea66486b4890f7c5a3769",
"mmlu_human_sexuality": "c3952ead23515a5207cf9f3100720f2e7e87afd423707745440088945f8652fb",
"mmlu_high_school_psychology": "fd2aba1beecb388fa7ac1516f3f164a8d4dfc003f1853302a0880b1f8fa98b69",
"mmlu_us_foreign_policy": "6687777c37a19360984ee099dbf3f398c1167e24f61e7a4144186493a5fcca8e",
"mmlu_professional_psychology": "8a0ad36605f937eecc2fb585d0b028799b532d91ba4635cac27c4edb64983588",
"mmlu_econometrics": "653c77934b037d0f9161ec45aaa98289aa3c5bc21b168f53f500afb0e2558de8",
"mmlu_public_relations": "4ab2f842b7193f7772b86b93907ae5e95602e1d0ab4d34bd8ffcd90eb636749a",
"mmlu_high_school_macroeconomics": "9cb4eb0918a560ad4eb14644e75098ceb31fb47c2ddcb3d5cd0cfb453f42943f",
"mmlu_high_school_geography": "1a7250b1bc9da6c95e32a1355cbfb55eafec79205473a02dd4e5b2dca62ee8b5",
"mmlu_sociology": "94c24d5267dc4641df7050f706238d02da6bd59c9d13308b91f6f3e2e3c766df",
"mmlu_high_school_government_and_politics": "fcb0e289d3d0b54c0dfd0d617a4e62181dfad12416a204d72d841fd4a99b8d9e",
"mmlu_security_studies": "a17e8fdfdda63b0f637ee0708501ecf5726cb76e4202b1fd79caab408ee2643d",
"mmlu_high_school_microeconomics": "383542db869a76d567e7c38637673e1b793c9b50b12fa9b0f65f68148a11787f",
"mmlu_jurisprudence": "d1324a2503964003b6f8f1e2f0245f1119c12dd113203ad292736bac9a91a350",
"mmlu_international_law": "38a92f06a96a87e69e12e82169bb7bd6f10f6b8adc61be20a9c68c0469d1d33d",
"mmlu_moral_scenarios": "729862e143b7bdaeaaf8169163162bd57c908d073ce7ea91737b605456026ed0",
"mmlu_philosophy": "763992eefbcda260efa16ebc995f09d244a6c8de4d61cb42ee1d7a9c5ca39543",
"mmlu_high_school_world_history": "5b4e5fc132b2d94b43add2e24e3f7284551a8be325948d6bcbb71c9f6bc2392c",
"mmlu_formal_logic": "fa096943ff3545d7d2fc3ac78194a0c1f352444e866511eb7737f06fbc8a7c9c",
"mmlu_high_school_us_history": "15ba64945d9a5fcf19245da1fb2663f9dedfeeb57f5515d37819f5de22e66a07",
"mmlu_moral_disputes": "39c141acc54f689a80e10e8615e1f62d581f09098edde4d389b1c13e92d4b49f",
"mmlu_logical_fallacies": "79ae47f5687483604531efbfd296a1edfa2a55facce333d43223b4a8fdf8780b",
"mmlu_high_school_european_history": "9d566a9a0b4521a56e56da75853682cbf6bee3f508101ae30e9516f2a1b42a15",
"mmlu_world_religions": "f8ec050ecd0217b3f863b199b03792909c78f6daee67ec5018d8f3ef92ccfd83",
"mmlu_prehistory": "cf0233bf3e56c9e67668dac16aed89d1721a87edb1456c4168493459ec3e4b28",
"mmlu_professional_law": "80161dc5f1a2d756815ce70fa33c5846e5b326aeb46b6fdccaa05a91a34a3c05"
},
"model_source": "hf",
"model_name": "tiiuae/Falcon3-7B-Instruct",
"model_name_sanitized": "tiiuae__Falcon3-7B-Instruct",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": false,
"chat_template": null,
"chat_template_sha": null,
"start_time": 612094.256100895,
"end_time": 612237.200732146,
"total_evaluation_time_seconds": "142.94463125104085"
}