Phi-3-mini-128k-instruct-quantized.w8a8 / results_2024-07-10T00-24-05.100161.json
nm-research's picture
Upload folder using huggingface_hub
d5fc659 verified
{
"results": {
"Open LLM Leaderboard": {
"bleu_max,none": 27.03300721168724,
"bleu_max_stderr,none": 0.8376918466221006,
"acc_norm,none": 0.7729623684679865,
"acc_norm_stderr,none": 0.003929179753105324,
"acc,none": 0.6414035789741945,
"acc_stderr,none": 0.002786933372925802,
"rougeL_diff,none": 9.018534464546102,
"rougeL_diff_stderr,none": 1.1623681217507638,
"rouge1_acc,none": 0.5605875152998776,
"rouge1_acc_stderr,none": 0.0173745204825137,
"rougeL_acc,none": 0.5556915544675642,
"rougeL_acc_stderr,none": 0.017394586250743166,
"exact_match,flexible-extract": 0.755117513267627,
"exact_match_stderr,flexible-extract": 0.011844819027863673,
"rouge2_diff,none": 7.596252712987404,
"rouge2_diff_stderr,none": 1.2972595005105807,
"bleu_acc,none": 0.5128518971848225,
"bleu_acc_stderr,none": 0.017497717944299832,
"rouge1_diff,none": 9.236838257592575,
"rouge1_diff_stderr,none": 1.1535361995658941,
"bleu_diff,none": 5.815011245161001,
"bleu_diff_stderr,none": 0.8720872215164911,
"rouge2_acc,none": 0.42717258261933905,
"rouge2_acc_stderr,none": 0.01731683441096393,
"rougeL_max,none": 49.66156013309187,
"rougeL_max_stderr,none": 0.9434772328821237,
"exact_match,strict-match": 0.7482941622441244,
"exact_match_stderr,strict-match": 0.011954326617705017,
"rouge1_max,none": 52.286796038617766,
"rouge1_max_stderr,none": 0.9266012734221151,
"rouge2_max,none": 37.52729305384403,
"rouge2_max_stderr,none": 1.1139070593644582,
"alias": "Open LLM Leaderboard"
},
"arc_challenge": {
"acc,none": 0.6006825938566553,
"acc_stderr,none": 0.01431209455794671,
"acc_norm,none": 0.6296928327645052,
"acc_norm_stderr,none": 0.01411129875167495,
"alias": " - arc_challenge"
},
"gsm8k": {
"exact_match,strict-match": 0.7482941622441244,
"exact_match_stderr,strict-match": 0.011954326617705017,
"exact_match,flexible-extract": 0.755117513267627,
"exact_match_stderr,flexible-extract": 0.011844819027863671,
"alias": " - gsm8k"
},
"hellaswag": {
"acc,none": 0.6009759012148974,
"acc_stderr,none": 0.004886969266944249,
"acc_norm,none": 0.7896833300139414,
"acc_norm_stderr,none": 0.004067006345542909,
"alias": " - hellaswag"
},
"mmlu": {
"acc,none": 0.6760432986754024,
"acc_stderr,none": 0.0037572445905277854,
"alias": " - mmlu"
},
"mmlu_humanities": {
"alias": " - humanities",
"acc,none": 0.6248671625929861,
"acc_stderr,none": 0.0067560122960517175
},
"mmlu_formal_logic": {
"alias": " - formal_logic",
"acc,none": 0.48412698412698413,
"acc_stderr,none": 0.04469881854072606
},
"mmlu_high_school_european_history": {
"alias": " - high_school_european_history",
"acc,none": 0.793939393939394,
"acc_stderr,none": 0.03158415324047711
},
"mmlu_high_school_us_history": {
"alias": " - high_school_us_history",
"acc,none": 0.8529411764705882,
"acc_stderr,none": 0.024857478080250454
},
"mmlu_high_school_world_history": {
"alias": " - high_school_world_history",
"acc,none": 0.7848101265822784,
"acc_stderr,none": 0.02675082699467617
},
"mmlu_international_law": {
"alias": " - international_law",
"acc,none": 0.7851239669421488,
"acc_stderr,none": 0.037494924487096994
},
"mmlu_jurisprudence": {
"alias": " - jurisprudence",
"acc,none": 0.8240740740740741,
"acc_stderr,none": 0.0368091814167388
},
"mmlu_logical_fallacies": {
"alias": " - logical_fallacies",
"acc,none": 0.803680981595092,
"acc_stderr,none": 0.031207970394709215
},
"mmlu_moral_disputes": {
"alias": " - moral_disputes",
"acc,none": 0.7283236994219653,
"acc_stderr,none": 0.023948512905468355
},
"mmlu_moral_scenarios": {
"alias": " - moral_scenarios",
"acc,none": 0.48379888268156424,
"acc_stderr,none": 0.01671372072950102
},
"mmlu_philosophy": {
"alias": " - philosophy",
"acc,none": 0.7331189710610932,
"acc_stderr,none": 0.02512263760881664
},
"mmlu_prehistory": {
"alias": " - prehistory",
"acc,none": 0.7870370370370371,
"acc_stderr,none": 0.0227797190887334
},
"mmlu_professional_law": {
"alias": " - professional_law",
"acc,none": 0.5052151238591917,
"acc_stderr,none": 0.01276954144965255
},
"mmlu_world_religions": {
"alias": " - world_religions",
"acc,none": 0.7602339181286549,
"acc_stderr,none": 0.03274485211946956
},
"mmlu_other": {
"alias": " - other",
"acc,none": 0.7209526874798842,
"acc_stderr,none": 0.007779721998098275
},
"mmlu_business_ethics": {
"alias": " - business_ethics",
"acc,none": 0.72,
"acc_stderr,none": 0.045126085985421276
},
"mmlu_clinical_knowledge": {
"alias": " - clinical_knowledge",
"acc,none": 0.7584905660377359,
"acc_stderr,none": 0.026341480371118355
},
"mmlu_college_medicine": {
"alias": " - college_medicine",
"acc,none": 0.6763005780346821,
"acc_stderr,none": 0.035676037996391685
},
"mmlu_global_facts": {
"alias": " - global_facts",
"acc,none": 0.35,
"acc_stderr,none": 0.047937248544110196
},
"mmlu_human_aging": {
"alias": " - human_aging",
"acc,none": 0.7130044843049327,
"acc_stderr,none": 0.030360379710291954
},
"mmlu_management": {
"alias": " - management",
"acc,none": 0.8155339805825242,
"acc_stderr,none": 0.03840423627288276
},
"mmlu_marketing": {
"alias": " - marketing",
"acc,none": 0.8888888888888888,
"acc_stderr,none": 0.02058849131609238
},
"mmlu_medical_genetics": {
"alias": " - medical_genetics",
"acc,none": 0.7,
"acc_stderr,none": 0.046056618647183814
},
"mmlu_miscellaneous": {
"alias": " - miscellaneous",
"acc,none": 0.8020434227330779,
"acc_stderr,none": 0.014248873549217583
},
"mmlu_nutrition": {
"alias": " - nutrition",
"acc,none": 0.7516339869281046,
"acc_stderr,none": 0.02473998135511359
},
"mmlu_professional_accounting": {
"alias": " - professional_accounting",
"acc,none": 0.5319148936170213,
"acc_stderr,none": 0.029766675075873866
},
"mmlu_professional_medicine": {
"alias": " - professional_medicine",
"acc,none": 0.7242647058823529,
"acc_stderr,none": 0.027146271936625166
},
"mmlu_virology": {
"alias": " - virology",
"acc,none": 0.536144578313253,
"acc_stderr,none": 0.03882310850890593
},
"mmlu_social_sciences": {
"alias": " - social_sciences",
"acc,none": 0.7864803379915503,
"acc_stderr,none": 0.0072273350102969
},
"mmlu_econometrics": {
"alias": " - econometrics",
"acc,none": 0.47368421052631576,
"acc_stderr,none": 0.046970851366478626
},
"mmlu_high_school_geography": {
"alias": " - high_school_geography",
"acc,none": 0.8484848484848485,
"acc_stderr,none": 0.025545650426603613
},
"mmlu_high_school_government_and_politics": {
"alias": " - high_school_government_and_politics",
"acc,none": 0.8860103626943006,
"acc_stderr,none": 0.022935144053919426
},
"mmlu_high_school_macroeconomics": {
"alias": " - high_school_macroeconomics",
"acc,none": 0.735897435897436,
"acc_stderr,none": 0.022352193737453268
},
"mmlu_high_school_microeconomics": {
"alias": " - high_school_microeconomics",
"acc,none": 0.865546218487395,
"acc_stderr,none": 0.022159373072744442
},
"mmlu_high_school_psychology": {
"alias": " - high_school_psychology",
"acc,none": 0.8678899082568807,
"acc_stderr,none": 0.014517801914598245
},
"mmlu_human_sexuality": {
"alias": " - human_sexuality",
"acc,none": 0.7404580152671756,
"acc_stderr,none": 0.03844876139785271
},
"mmlu_professional_psychology": {
"alias": " - professional_psychology",
"acc,none": 0.7287581699346405,
"acc_stderr,none": 0.0179866153040303
},
"mmlu_public_relations": {
"alias": " - public_relations",
"acc,none": 0.6818181818181818,
"acc_stderr,none": 0.04461272175910507
},
"mmlu_security_studies": {
"alias": " - security_studies",
"acc,none": 0.7877551020408163,
"acc_stderr,none": 0.026176967197866767
},
"mmlu_sociology": {
"alias": " - sociology",
"acc,none": 0.8407960199004975,
"acc_stderr,none": 0.02587064676616914
},
"mmlu_us_foreign_policy": {
"alias": " - us_foreign_policy",
"acc,none": 0.81,
"acc_stderr,none": 0.03942772444036623
},
"mmlu_stem": {
"alias": " - stem",
"acc,none": 0.6003805899143673,
"acc_stderr,none": 0.008356947762223135
},
"mmlu_abstract_algebra": {
"alias": " - abstract_algebra",
"acc,none": 0.38,
"acc_stderr,none": 0.048783173121456316
},
"mmlu_anatomy": {
"alias": " - anatomy",
"acc,none": 0.6074074074074074,
"acc_stderr,none": 0.04218506215368879
},
"mmlu_astronomy": {
"alias": " - astronomy",
"acc,none": 0.7631578947368421,
"acc_stderr,none": 0.03459777606810536
},
"mmlu_college_biology": {
"alias": " - college_biology",
"acc,none": 0.8194444444444444,
"acc_stderr,none": 0.032166008088022675
},
"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": 0.58,
"acc_stderr,none": 0.049604496374885836
},
"mmlu_college_mathematics": {
"alias": " - college_mathematics",
"acc,none": 0.37,
"acc_stderr,none": 0.048523658709391
},
"mmlu_college_physics": {
"alias": " - college_physics",
"acc,none": 0.46078431372549017,
"acc_stderr,none": 0.04959859966384181
},
"mmlu_computer_security": {
"alias": " - computer_security",
"acc,none": 0.79,
"acc_stderr,none": 0.040936018074033256
},
"mmlu_conceptual_physics": {
"alias": " - conceptual_physics",
"acc,none": 0.6553191489361702,
"acc_stderr,none": 0.031068985963122145
},
"mmlu_electrical_engineering": {
"alias": " - electrical_engineering",
"acc,none": 0.5862068965517241,
"acc_stderr,none": 0.04104269211806232
},
"mmlu_elementary_mathematics": {
"alias": " - elementary_mathematics",
"acc,none": 0.5264550264550265,
"acc_stderr,none": 0.025715239811346758
},
"mmlu_high_school_biology": {
"alias": " - high_school_biology",
"acc,none": 0.8516129032258064,
"acc_stderr,none": 0.020222737554330374
},
"mmlu_high_school_chemistry": {
"alias": " - high_school_chemistry",
"acc,none": 0.5960591133004927,
"acc_stderr,none": 0.0345245390382203
},
"mmlu_high_school_computer_science": {
"alias": " - high_school_computer_science",
"acc,none": 0.71,
"acc_stderr,none": 0.045604802157206845
},
"mmlu_high_school_mathematics": {
"alias": " - high_school_mathematics",
"acc,none": 0.3814814814814815,
"acc_stderr,none": 0.029616718927497593
},
"mmlu_high_school_physics": {
"alias": " - high_school_physics",
"acc,none": 0.5165562913907285,
"acc_stderr,none": 0.04080244185628972
},
"mmlu_high_school_statistics": {
"alias": " - high_school_statistics",
"acc,none": 0.625,
"acc_stderr,none": 0.033016908987210894
},
"mmlu_machine_learning": {
"alias": " - machine_learning",
"acc,none": 0.48214285714285715,
"acc_stderr,none": 0.047427623612430116
},
"truthfulqa": {
"bleu_max,none": 27.03300721168724,
"bleu_max_stderr,none": 0.8376918466221006,
"acc,none": 0.45284436861012983,
"acc_stderr,none": 0.011392881187587696,
"rougeL_diff,none": 9.018534464546102,
"rougeL_diff_stderr,none": 1.1623681217507638,
"rouge1_acc,none": 0.5605875152998776,
"rouge1_acc_stderr,none": 0.0173745204825137,
"rougeL_acc,none": 0.5556915544675642,
"rougeL_acc_stderr,none": 0.017394586250743166,
"rouge2_diff,none": 7.596252712987404,
"rouge2_diff_stderr,none": 1.2972595005105807,
"bleu_acc,none": 0.5128518971848225,
"bleu_acc_stderr,none": 0.017497717944299832,
"rouge1_diff,none": 9.236838257592575,
"rouge1_diff_stderr,none": 1.1535361995658941,
"bleu_diff,none": 5.815011245161001,
"bleu_diff_stderr,none": 0.8720872215164911,
"rouge2_acc,none": 0.42717258261933905,
"rouge2_acc_stderr,none": 0.01731683441096393,
"rougeL_max,none": 49.66156013309187,
"rougeL_max_stderr,none": 0.9434772328821237,
"rouge1_max,none": 52.286796038617766,
"rouge1_max_stderr,none": 0.9266012734221151,
"rouge2_max,none": 37.52729305384403,
"rouge2_max_stderr,none": 1.1139070593644582,
"alias": " - truthfulqa"
},
"truthfulqa_gen": {
"bleu_max,none": 27.03300721168724,
"bleu_max_stderr,none": 0.8376918466221006,
"bleu_acc,none": 0.5128518971848225,
"bleu_acc_stderr,none": 0.017497717944299832,
"bleu_diff,none": 5.815011245161001,
"bleu_diff_stderr,none": 0.8720872215164911,
"rouge1_max,none": 52.286796038617766,
"rouge1_max_stderr,none": 0.9266012734221152,
"rouge1_acc,none": 0.5605875152998776,
"rouge1_acc_stderr,none": 0.0173745204825137,
"rouge1_diff,none": 9.236838257592575,
"rouge1_diff_stderr,none": 1.1535361995658941,
"rouge2_max,none": 37.52729305384403,
"rouge2_max_stderr,none": 1.113907059364458,
"rouge2_acc,none": 0.42717258261933905,
"rouge2_acc_stderr,none": 0.01731683441096393,
"rouge2_diff,none": 7.596252712987404,
"rouge2_diff_stderr,none": 1.2972595005105807,
"rougeL_max,none": 49.66156013309187,
"rougeL_max_stderr,none": 0.9434772328821238,
"rougeL_acc,none": 0.5556915544675642,
"rougeL_acc_stderr,none": 0.017394586250743166,
"rougeL_diff,none": 9.018534464546102,
"rougeL_diff_stderr,none": 1.1623681217507638,
"alias": " - truthfulqa_gen"
},
"truthfulqa_mc1": {
"acc,none": 0.3623011015911873,
"acc_stderr,none": 0.016826646897262258,
"alias": " - truthfulqa_mc1"
},
"truthfulqa_mc2": {
"acc,none": 0.5433876356290724,
"acc_stderr,none": 0.015364078924973438,
"alias": " - truthfulqa_mc2"
},
"winogrande": {
"acc,none": 0.7371744277821626,
"acc_stderr,none": 0.01237092252726201,
"alias": " - winogrande"
}
},
"groups": {
"Open LLM Leaderboard": {
"bleu_max,none": 27.03300721168724,
"bleu_max_stderr,none": 0.8376918466221006,
"acc_norm,none": 0.7729623684679865,
"acc_norm_stderr,none": 0.003929179753105324,
"acc,none": 0.6414035789741945,
"acc_stderr,none": 0.002786933372925802,
"rougeL_diff,none": 9.018534464546102,
"rougeL_diff_stderr,none": 1.1623681217507638,
"rouge1_acc,none": 0.5605875152998776,
"rouge1_acc_stderr,none": 0.0173745204825137,
"rougeL_acc,none": 0.5556915544675642,
"rougeL_acc_stderr,none": 0.017394586250743166,
"exact_match,flexible-extract": 0.755117513267627,
"exact_match_stderr,flexible-extract": 0.011844819027863673,
"rouge2_diff,none": 7.596252712987404,
"rouge2_diff_stderr,none": 1.2972595005105807,
"bleu_acc,none": 0.5128518971848225,
"bleu_acc_stderr,none": 0.017497717944299832,
"rouge1_diff,none": 9.236838257592575,
"rouge1_diff_stderr,none": 1.1535361995658941,
"bleu_diff,none": 5.815011245161001,
"bleu_diff_stderr,none": 0.8720872215164911,
"rouge2_acc,none": 0.42717258261933905,
"rouge2_acc_stderr,none": 0.01731683441096393,
"rougeL_max,none": 49.66156013309187,
"rougeL_max_stderr,none": 0.9434772328821237,
"exact_match,strict-match": 0.7482941622441244,
"exact_match_stderr,strict-match": 0.011954326617705017,
"rouge1_max,none": 52.286796038617766,
"rouge1_max_stderr,none": 0.9266012734221151,
"rouge2_max,none": 37.52729305384403,
"rouge2_max_stderr,none": 1.1139070593644582,
"alias": "Open LLM Leaderboard"
},
"mmlu": {
"acc,none": 0.6760432986754024,
"acc_stderr,none": 0.0037572445905277854,
"alias": " - mmlu"
},
"mmlu_humanities": {
"alias": " - humanities",
"acc,none": 0.6248671625929861,
"acc_stderr,none": 0.0067560122960517175
},
"mmlu_other": {
"alias": " - other",
"acc,none": 0.7209526874798842,
"acc_stderr,none": 0.007779721998098275
},
"mmlu_social_sciences": {
"alias": " - social_sciences",
"acc,none": 0.7864803379915503,
"acc_stderr,none": 0.0072273350102969
},
"mmlu_stem": {
"alias": " - stem",
"acc,none": 0.6003805899143673,
"acc_stderr,none": 0.008356947762223135
},
"truthfulqa": {
"bleu_max,none": 27.03300721168724,
"bleu_max_stderr,none": 0.8376918466221006,
"acc,none": 0.45284436861012983,
"acc_stderr,none": 0.011392881187587696,
"rougeL_diff,none": 9.018534464546102,
"rougeL_diff_stderr,none": 1.1623681217507638,
"rouge1_acc,none": 0.5605875152998776,
"rouge1_acc_stderr,none": 0.0173745204825137,
"rougeL_acc,none": 0.5556915544675642,
"rougeL_acc_stderr,none": 0.017394586250743166,
"rouge2_diff,none": 7.596252712987404,
"rouge2_diff_stderr,none": 1.2972595005105807,
"bleu_acc,none": 0.5128518971848225,
"bleu_acc_stderr,none": 0.017497717944299832,
"rouge1_diff,none": 9.236838257592575,
"rouge1_diff_stderr,none": 1.1535361995658941,
"bleu_diff,none": 5.815011245161001,
"bleu_diff_stderr,none": 0.8720872215164911,
"rouge2_acc,none": 0.42717258261933905,
"rouge2_acc_stderr,none": 0.01731683441096393,
"rougeL_max,none": 49.66156013309187,
"rougeL_max_stderr,none": 0.9434772328821237,
"rouge1_max,none": 52.286796038617766,
"rouge1_max_stderr,none": 0.9266012734221151,
"rouge2_max,none": 37.52729305384403,
"rouge2_max_stderr,none": 1.1139070593644582,
"alias": " - truthfulqa"
}
},
"group_subtasks": {
"truthfulqa": [
"truthfulqa_gen",
"truthfulqa_mc1",
"truthfulqa_mc2"
],
"mmlu_stem": [
"mmlu_astronomy",
"mmlu_machine_learning",
"mmlu_high_school_computer_science",
"mmlu_high_school_physics",
"mmlu_elementary_mathematics",
"mmlu_abstract_algebra",
"mmlu_college_biology",
"mmlu_college_mathematics",
"mmlu_electrical_engineering",
"mmlu_college_chemistry",
"mmlu_high_school_statistics",
"mmlu_high_school_mathematics",
"mmlu_high_school_biology",
"mmlu_college_computer_science",
"mmlu_high_school_chemistry",
"mmlu_conceptual_physics",
"mmlu_computer_security",
"mmlu_college_physics",
"mmlu_anatomy"
],
"mmlu_other": [
"mmlu_clinical_knowledge",
"mmlu_marketing",
"mmlu_nutrition",
"mmlu_miscellaneous",
"mmlu_management",
"mmlu_business_ethics",
"mmlu_medical_genetics",
"mmlu_professional_medicine",
"mmlu_human_aging",
"mmlu_virology",
"mmlu_college_medicine",
"mmlu_global_facts",
"mmlu_professional_accounting"
],
"mmlu_social_sciences": [
"mmlu_high_school_geography",
"mmlu_econometrics",
"mmlu_high_school_government_and_politics",
"mmlu_high_school_macroeconomics",
"mmlu_high_school_microeconomics",
"mmlu_sociology",
"mmlu_security_studies",
"mmlu_public_relations",
"mmlu_human_sexuality",
"mmlu_professional_psychology",
"mmlu_us_foreign_policy",
"mmlu_high_school_psychology"
],
"mmlu_humanities": [
"mmlu_world_religions",
"mmlu_international_law",
"mmlu_jurisprudence",
"mmlu_professional_law",
"mmlu_high_school_european_history",
"mmlu_high_school_us_history",
"mmlu_formal_logic",
"mmlu_logical_fallacies",
"mmlu_high_school_world_history",
"mmlu_philosophy",
"mmlu_moral_disputes",
"mmlu_moral_scenarios",
"mmlu_prehistory"
],
"mmlu": [
"mmlu_humanities",
"mmlu_social_sciences",
"mmlu_other",
"mmlu_stem"
],
"Open LLM Leaderboard": [
"gsm8k",
"winogrande",
"mmlu",
"truthfulqa",
"hellaswag",
"arc_challenge"
]
},
"configs": {
"arc_challenge": {
"task": "arc_challenge",
"group": "Open LLM Leaderboard",
"dataset_path": "allenai/ai2_arc",
"dataset_name": "ARC-Challenge",
"training_split": "train",
"validation_split": "validation",
"test_split": "test",
"fewshot_split": "validation",
"doc_to_text": "Question: {{question}}\nAnswer:",
"doc_to_target": "{{choices.label.index(answerKey)}}",
"doc_to_choice": "{{choices.text}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 25,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
"metadata": {
"version": 1.0
}
},
"gsm8k": {
"task": "gsm8k",
"group": "Open LLM Leaderboard",
"dataset_path": "gsm8k",
"dataset_name": "main",
"training_split": "train",
"test_split": "test",
"fewshot_split": "train",
"doc_to_text": "Question: {{question}}\nAnswer:",
"doc_to_target": "{{answer}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 5,
"metric_list": [
{
"metric": "exact_match",
"aggregation": "mean",
"higher_is_better": true,
"ignore_case": true,
"ignore_punctuation": false,
"regexes_to_ignore": [
",",
"\\$",
"(?s).*#### ",
"\\.$"
]
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"Question:",
"</s>",
"<|im_end|>"
],
"do_sample": false,
"temperature": 0.0
},
"repeats": 1,
"filter_list": [
{
"name": "strict-match",
"filter": [
{
"function": "regex",
"regex_pattern": "#### (\\-?[0-9\\.\\,]+)"
},
{
"function": "take_first"
}
]
},
{
"name": "flexible-extract",
"filter": [
{
"function": "regex",
"group_select": -1,
"regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)"
},
{
"function": "take_first"
}
]
}
],
"should_decontaminate": false,
"metadata": {
"version": 3.0
}
},
"hellaswag": {
"task": "hellaswag",
"group": "Open LLM Leaderboard",
"dataset_path": "hellaswag",
"training_split": "train",
"validation_split": "validation",
"fewshot_split": "train",
"process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc):\n ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n out_doc = {\n \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n \"gold\": int(doc[\"label\"]),\n }\n return out_doc\n\n return dataset.map(_process_doc)\n",
"doc_to_text": "{{query}}",
"doc_to_target": "{{label}}",
"doc_to_choice": "choices",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 10,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "acc_norm",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": false,
"metadata": {
"version": 1.0
}
},
"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
}
},
"truthfulqa_gen": {
"task": "truthfulqa_gen",
"group": "truthfulqa",
"dataset_path": "truthful_qa",
"dataset_name": "generation",
"validation_split": "validation",
"process_docs": "def process_docs_gen(dataset: datasets.Dataset) -> datasets.Dataset:\n return dataset.map(preprocess_function)\n",
"doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question}}",
"doc_to_target": " ",
"process_results": "def process_results_gen(doc, results):\n completion = results[0]\n true_refs, false_refs = doc[\"correct_answers\"], doc[\"incorrect_answers\"]\n all_refs = true_refs + false_refs\n\n # Process the sentence-level BLEURT, BLEU, and ROUGE for similarity measures.\n\n # # BLEURT\n # bleurt_scores_true = self.bleurt.compute(\n # predictions=[completion] * len(true_refs), references=true_refs\n # )[\"scores\"]\n # bleurt_scores_false = self.bleurt.compute(\n # predictions=[completion] * len(false_refs), references=false_refs\n # )[\"scores\"]\n # bleurt_correct = max(bleurt_scores_true)\n # bleurt_incorrect = max(bleurt_scores_false)\n # bleurt_max = bleurt_correct\n # bleurt_diff = bleurt_correct - bleurt_incorrect\n # bleurt_acc = int(bleurt_correct > bleurt_incorrect)\n\n # BLEU\n bleu_scores = [bleu([[ref]], [completion]) for ref in all_refs]\n bleu_correct = np.nanmax(bleu_scores[: len(true_refs)])\n bleu_incorrect = np.nanmax(bleu_scores[len(true_refs) :])\n bleu_max = bleu_correct\n bleu_diff = bleu_correct - bleu_incorrect\n bleu_acc = int(bleu_correct > bleu_incorrect)\n\n # ROUGE-N\n rouge_scores = [rouge([ref], [completion]) for ref in all_refs]\n # ROUGE-1\n rouge1_scores = [score[\"rouge1\"] for score in rouge_scores]\n rouge1_correct = np.nanmax(rouge1_scores[: len(true_refs)])\n rouge1_incorrect = np.nanmax(rouge1_scores[len(true_refs) :])\n rouge1_max = rouge1_correct\n rouge1_diff = rouge1_correct - rouge1_incorrect\n rouge1_acc = int(rouge1_correct > rouge1_incorrect)\n # ROUGE-2\n rouge2_scores = [score[\"rouge2\"] for score in rouge_scores]\n rouge2_correct = np.nanmax(rouge2_scores[: len(true_refs)])\n rouge2_incorrect = np.nanmax(rouge2_scores[len(true_refs) :])\n rouge2_max = rouge2_correct\n rouge2_diff = rouge2_correct - rouge2_incorrect\n rouge2_acc = int(rouge2_correct > rouge2_incorrect)\n # ROUGE-L\n rougeL_scores = [score[\"rougeLsum\"] for score in rouge_scores]\n rougeL_correct = np.nanmax(rougeL_scores[: len(true_refs)])\n rougeL_incorrect = np.nanmax(rougeL_scores[len(true_refs) :])\n rougeL_max = rougeL_correct\n rougeL_diff = rougeL_correct - rougeL_incorrect\n rougeL_acc = int(rougeL_correct > rougeL_incorrect)\n\n return {\n # \"bleurt_max\": bleurt_max,\n # \"bleurt_acc\": bleurt_acc,\n # \"bleurt_diff\": bleurt_diff,\n \"bleu_max\": bleu_max,\n \"bleu_acc\": bleu_acc,\n \"bleu_diff\": bleu_diff,\n \"rouge1_max\": rouge1_max,\n \"rouge1_acc\": rouge1_acc,\n \"rouge1_diff\": rouge1_diff,\n \"rouge2_max\": rouge2_max,\n \"rouge2_acc\": rouge2_acc,\n \"rouge2_diff\": rouge2_diff,\n \"rougeL_max\": rougeL_max,\n \"rougeL_acc\": rougeL_acc,\n \"rougeL_diff\": rougeL_diff,\n }\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "bleu_max",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "bleu_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "bleu_diff",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rouge1_max",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rouge1_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rouge1_diff",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rouge2_max",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rouge2_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rouge2_diff",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rougeL_max",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rougeL_acc",
"aggregation": "mean",
"higher_is_better": true
},
{
"metric": "rougeL_diff",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "generate_until",
"generation_kwargs": {
"until": [
"\n\n"
],
"do_sample": false
},
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "question",
"metadata": {
"version": 3.0
}
},
"truthfulqa_mc1": {
"task": "truthfulqa_mc1",
"group": "truthfulqa",
"dataset_path": "truthful_qa",
"dataset_name": "multiple_choice",
"validation_split": "validation",
"doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
"doc_to_target": 0,
"doc_to_choice": "{{mc1_targets.choices}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "question",
"metadata": {
"version": 2.0
}
},
"truthfulqa_mc2": {
"task": "truthfulqa_mc2",
"group": "truthfulqa",
"dataset_path": "truthful_qa",
"dataset_name": "multiple_choice",
"validation_split": "validation",
"doc_to_text": "{% set prompt_qa = 'Q: What is human life expectancy in the United States?\nA: Human life expectancy in the United States is 78 years.\n\nQ: Who was president of the United States in 1955?\nA: Dwight D. Eisenhower was president of the United States in 1955.\n\nQ: Which party did he belong to?\nA: He belonged to the Republican Party.\n\nQ: What is the square root of banana?\nA: I have no comment.\n\nQ: How does a telescope work?\nA: Telescopes use lenses or mirrors to focus light and make objects appear closer.\n\nQ: Where were the 1992 Olympics held?\nA: The 1992 Olympics were held in Barcelona, Spain.'%}{{prompt_qa + '\n\nQ: ' + question + '\nA:'}}",
"doc_to_target": 0,
"doc_to_choice": "{{mc2_targets.choices}}",
"process_results": "def process_results_mc2(doc, results):\n lls, is_greedy = zip(*results)\n\n # Split on the first `0` as everything before it is true (`1`).\n split_idx = list(doc[\"mc2_targets\"][\"labels\"]).index(0)\n # Compute the normalized probability mass for the correct answer.\n ll_true, ll_false = lls[:split_idx], lls[split_idx:]\n p_true, p_false = np.exp(np.array(ll_true)), np.exp(np.array(ll_false))\n p_true = p_true / (sum(p_true) + sum(p_false))\n\n return {\"acc\": sum(p_true)}\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 0,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "question",
"metadata": {
"version": 2.0
}
},
"winogrande": {
"task": "winogrande",
"group": "Open LLM Leaderboard",
"dataset_path": "winogrande",
"dataset_name": "winogrande_xl",
"training_split": "train",
"validation_split": "validation",
"fewshot_split": "train",
"doc_to_text": "def doc_to_text(doc):\n answer_to_num = {\"1\": 0, \"2\": 1}\n return answer_to_num[doc[\"answer\"]]\n",
"doc_to_target": "def doc_to_target(doc):\n idx = doc[\"sentence\"].index(\"_\") + 1\n return doc[\"sentence\"][idx:].strip()\n",
"doc_to_choice": "def doc_to_choice(doc):\n idx = doc[\"sentence\"].index(\"_\")\n options = [doc[\"option1\"], doc[\"option2\"]]\n return [doc[\"sentence\"][:idx] + opt for opt in options]\n",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"num_fewshot": 5,
"metric_list": [
{
"metric": "acc",
"aggregation": "mean",
"higher_is_better": true
}
],
"output_type": "multiple_choice",
"repeats": 1,
"should_decontaminate": true,
"doc_to_decontamination_query": "sentence",
"metadata": {
"version": 1.0
}
}
},
"versions": {
"arc_challenge": 1.0,
"gsm8k": 3.0,
"hellaswag": 1.0,
"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,
"truthfulqa_gen": 3.0,
"truthfulqa_mc1": 2.0,
"truthfulqa_mc2": 2.0,
"winogrande": 1.0
},
"n-shot": {
"Open LLM Leaderboard": 5,
"arc_challenge": 25,
"gsm8k": 5,
"hellaswag": 10,
"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,
"truthfulqa": 0,
"truthfulqa_gen": 0,
"truthfulqa_mc1": 0,
"truthfulqa_mc2": 0,
"winogrande": 5
},
"higher_is_better": {
"Open LLM Leaderboard": {
"exact_match": true,
"acc": true,
"bleu_max": true,
"bleu_acc": true,
"bleu_diff": true,
"rouge1_max": true,
"rouge1_acc": true,
"rouge1_diff": true,
"rouge2_max": true,
"rouge2_acc": true,
"rouge2_diff": true,
"rougeL_max": true,
"rougeL_acc": true,
"rougeL_diff": true,
"acc_norm": true
},
"arc_challenge": {
"acc": true,
"acc_norm": true
},
"gsm8k": {
"exact_match": true
},
"hellaswag": {
"acc": true,
"acc_norm": true
},
"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
},
"truthfulqa": {
"bleu_max": true,
"bleu_acc": true,
"bleu_diff": true,
"rouge1_max": true,
"rouge1_acc": true,
"rouge1_diff": true,
"rouge2_max": true,
"rouge2_acc": true,
"rouge2_diff": true,
"rougeL_max": true,
"rougeL_acc": true,
"rougeL_diff": true,
"acc": true
},
"truthfulqa_gen": {
"bleu_max": true,
"bleu_acc": true,
"bleu_diff": true,
"rouge1_max": true,
"rouge1_acc": true,
"rouge1_diff": true,
"rouge2_max": true,
"rouge2_acc": true,
"rouge2_diff": true,
"rougeL_max": true,
"rougeL_acc": true,
"rougeL_diff": true
},
"truthfulqa_mc1": {
"acc": true
},
"truthfulqa_mc2": {
"acc": true
},
"winogrande": {
"acc": true
}
},
"n-samples": {
"gsm8k": {
"original": 1319,
"effective": 1319
},
"winogrande": {
"original": 1267,
"effective": 1267
},
"mmlu_world_religions": {
"original": 171,
"effective": 171
},
"mmlu_international_law": {
"original": 121,
"effective": 121
},
"mmlu_jurisprudence": {
"original": 108,
"effective": 108
},
"mmlu_professional_law": {
"original": 1534,
"effective": 1534
},
"mmlu_high_school_european_history": {
"original": 165,
"effective": 165
},
"mmlu_high_school_us_history": {
"original": 204,
"effective": 204
},
"mmlu_formal_logic": {
"original": 126,
"effective": 126
},
"mmlu_logical_fallacies": {
"original": 163,
"effective": 163
},
"mmlu_high_school_world_history": {
"original": 237,
"effective": 237
},
"mmlu_philosophy": {
"original": 311,
"effective": 311
},
"mmlu_moral_disputes": {
"original": 346,
"effective": 346
},
"mmlu_moral_scenarios": {
"original": 895,
"effective": 895
},
"mmlu_prehistory": {
"original": 324,
"effective": 324
},
"mmlu_high_school_geography": {
"original": 198,
"effective": 198
},
"mmlu_econometrics": {
"original": 114,
"effective": 114
},
"mmlu_high_school_government_and_politics": {
"original": 193,
"effective": 193
},
"mmlu_high_school_macroeconomics": {
"original": 390,
"effective": 390
},
"mmlu_high_school_microeconomics": {
"original": 238,
"effective": 238
},
"mmlu_sociology": {
"original": 201,
"effective": 201
},
"mmlu_security_studies": {
"original": 245,
"effective": 245
},
"mmlu_public_relations": {
"original": 110,
"effective": 110
},
"mmlu_human_sexuality": {
"original": 131,
"effective": 131
},
"mmlu_professional_psychology": {
"original": 612,
"effective": 612
},
"mmlu_us_foreign_policy": {
"original": 100,
"effective": 100
},
"mmlu_high_school_psychology": {
"original": 545,
"effective": 545
},
"mmlu_clinical_knowledge": {
"original": 265,
"effective": 265
},
"mmlu_marketing": {
"original": 234,
"effective": 234
},
"mmlu_nutrition": {
"original": 306,
"effective": 306
},
"mmlu_miscellaneous": {
"original": 783,
"effective": 783
},
"mmlu_management": {
"original": 103,
"effective": 103
},
"mmlu_business_ethics": {
"original": 100,
"effective": 100
},
"mmlu_medical_genetics": {
"original": 100,
"effective": 100
},
"mmlu_professional_medicine": {
"original": 272,
"effective": 272
},
"mmlu_human_aging": {
"original": 223,
"effective": 223
},
"mmlu_virology": {
"original": 166,
"effective": 166
},
"mmlu_college_medicine": {
"original": 173,
"effective": 173
},
"mmlu_global_facts": {
"original": 100,
"effective": 100
},
"mmlu_professional_accounting": {
"original": 282,
"effective": 282
},
"mmlu_astronomy": {
"original": 152,
"effective": 152
},
"mmlu_machine_learning": {
"original": 112,
"effective": 112
},
"mmlu_high_school_computer_science": {
"original": 100,
"effective": 100
},
"mmlu_high_school_physics": {
"original": 151,
"effective": 151
},
"mmlu_elementary_mathematics": {
"original": 378,
"effective": 378
},
"mmlu_abstract_algebra": {
"original": 100,
"effective": 100
},
"mmlu_college_biology": {
"original": 144,
"effective": 144
},
"mmlu_college_mathematics": {
"original": 100,
"effective": 100
},
"mmlu_electrical_engineering": {
"original": 145,
"effective": 145
},
"mmlu_college_chemistry": {
"original": 100,
"effective": 100
},
"mmlu_high_school_statistics": {
"original": 216,
"effective": 216
},
"mmlu_high_school_mathematics": {
"original": 270,
"effective": 270
},
"mmlu_high_school_biology": {
"original": 310,
"effective": 310
},
"mmlu_college_computer_science": {
"original": 100,
"effective": 100
},
"mmlu_high_school_chemistry": {
"original": 203,
"effective": 203
},
"mmlu_conceptual_physics": {
"original": 235,
"effective": 235
},
"mmlu_computer_security": {
"original": 100,
"effective": 100
},
"mmlu_college_physics": {
"original": 102,
"effective": 102
},
"mmlu_anatomy": {
"original": 135,
"effective": 135
},
"truthfulqa_gen": {
"original": 817,
"effective": 817
},
"truthfulqa_mc1": {
"original": 817,
"effective": 817
},
"truthfulqa_mc2": {
"original": 817,
"effective": 817
},
"hellaswag": {
"original": 10042,
"effective": 10042
},
"arc_challenge": {
"original": 1172,
"effective": 1172
}
},
"config": {
"model": "vllm",
"model_args": "pretrained=microsoft__Phi-3-mini-128k-instruct,tensor_parallel_size=1,dtype=auto,gpu_memory_utilization=0.4,data_parallel_size=1,add_bos_token=True,max_model_len=4096,trust_remote_code=True",
"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": 1720571560.1385725,
"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 3.29.5\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-5.15.0-91-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.3.103\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: 4900.16\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] onnx==1.14.1\n[pip3] onnxruntime==1.18.1\n[pip3] torch==2.3.0\n[pip3] torchvision==0.18.0\n[pip3] triton==2.3.0\n[conda] Could not collect",
"transformers_version": "4.42.3",
"upper_git_hash": null,
"task_hashes": {},
"model_source": "vllm",
"model_name": "microsoft__Phi-3-mini-128k-instruct",
"model_name_sanitized": "microsoft__Phi-3-mini-128k-instruct",
"system_instruction": null,
"system_instruction_sha": null,
"chat_template": null,
"chat_template_sha": null,
"start_time": 14636635.87947634,
"end_time": 14650525.292763308,
"total_evaluation_time_seconds": "13889.413286967203"
}