{ "results": { "harness|arc:challenge|25": { "acc": 0.5102389078498294, "acc_stderr": 0.014608326906285012, "acc_norm": 0.5426621160409556, "acc_norm_stderr": 0.014558106543924065 }, "harness|hellaswag|10": { "acc": 0.5862378012348137, "acc_stderr": 0.004915003499517829, "acc_norm": 0.7853017327225652, "acc_norm_stderr": 0.004097736838432052 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.48026315789473684, "acc_stderr": 0.040657710025626036, "acc_norm": 0.48026315789473684, "acc_norm_stderr": 0.040657710025626036 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.49056603773584906, "acc_stderr": 0.0307673947078081, "acc_norm": 0.49056603773584906, "acc_norm_stderr": 0.0307673947078081 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4791666666666667, "acc_stderr": 0.041775789507399935, "acc_norm": 0.4791666666666667, "acc_norm_stderr": 0.041775789507399935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.42196531791907516, "acc_stderr": 0.03765746693865151, "acc_norm": 0.42196531791907516, "acc_norm_stderr": 0.03765746693865151 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237657, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237657 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4, "acc_stderr": 0.03202563076101737, "acc_norm": 0.4, "acc_norm_stderr": 0.03202563076101737 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.22807017543859648, "acc_stderr": 0.03947152782669415, "acc_norm": 0.22807017543859648, "acc_norm_stderr": 0.03947152782669415 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3793103448275862, "acc_stderr": 0.04043461861916747, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.04043461861916747 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.23809523809523808, "acc_stderr": 0.021935878081184766, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.021935878081184766 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04216370213557835, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04216370213557835 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5129032258064516, "acc_stderr": 0.028434533152681855, "acc_norm": 0.5129032258064516, "acc_norm_stderr": 0.028434533152681855 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.0316185633535861, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.0316185633535861 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5757575757575758, "acc_stderr": 0.038592681420702636, "acc_norm": 0.5757575757575758, "acc_norm_stderr": 0.038592681420702636 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5151515151515151, "acc_stderr": 0.03560716516531061, "acc_norm": 0.5151515151515151, "acc_norm_stderr": 0.03560716516531061 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6580310880829016, "acc_stderr": 0.03423465100104283, "acc_norm": 0.6580310880829016, "acc_norm_stderr": 0.03423465100104283 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.43846153846153846, "acc_stderr": 0.025158266016868575, "acc_norm": 0.43846153846153846, "acc_norm_stderr": 0.025158266016868575 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2962962962962963, "acc_stderr": 0.027840811495871927, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.027840811495871927 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.44537815126050423, "acc_stderr": 0.0322841062671639, "acc_norm": 0.44537815126050423, "acc_norm_stderr": 0.0322841062671639 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.33774834437086093, "acc_stderr": 0.038615575462551684, "acc_norm": 0.33774834437086093, "acc_norm_stderr": 0.038615575462551684 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.5871559633027523, "acc_stderr": 0.021109128133413913, "acc_norm": 0.5871559633027523, "acc_norm_stderr": 0.021109128133413913 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.3472222222222222, "acc_stderr": 0.032468872436376486, "acc_norm": 0.3472222222222222, "acc_norm_stderr": 0.032468872436376486 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.5294117647058824, "acc_stderr": 0.03503235296367992, "acc_norm": 0.5294117647058824, "acc_norm_stderr": 0.03503235296367992 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.6244725738396625, "acc_stderr": 0.03152256243091156, "acc_norm": 0.6244725738396625, "acc_norm_stderr": 0.03152256243091156 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.5291479820627802, "acc_stderr": 0.03350073248773404, "acc_norm": 0.5291479820627802, "acc_norm_stderr": 0.03350073248773404 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.5343511450381679, "acc_stderr": 0.043749285605997376, "acc_norm": 0.5343511450381679, "acc_norm_stderr": 0.043749285605997376 }, "harness|hendrycksTest-international_law|5": { "acc": 0.6528925619834711, "acc_stderr": 0.04345724570292534, "acc_norm": 0.6528925619834711, "acc_norm_stderr": 0.04345724570292534 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.49074074074074076, "acc_stderr": 0.04832853553437055, "acc_norm": 0.49074074074074076, "acc_norm_stderr": 0.04832853553437055 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.4294478527607362, "acc_stderr": 0.03889066619112722, "acc_norm": 0.4294478527607362, "acc_norm_stderr": 0.03889066619112722 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.36607142857142855, "acc_stderr": 0.045723723587374296, "acc_norm": 0.36607142857142855, "acc_norm_stderr": 0.045723723587374296 }, "harness|hendrycksTest-management|5": { "acc": 0.5922330097087378, "acc_stderr": 0.0486577757041077, "acc_norm": 0.5922330097087378, "acc_norm_stderr": 0.0486577757041077 }, "harness|hendrycksTest-marketing|5": { "acc": 0.6495726495726496, "acc_stderr": 0.0312561082442188, "acc_norm": 0.6495726495726496, "acc_norm_stderr": 0.0312561082442188 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.6206896551724138, "acc_stderr": 0.01735126811754445, "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.01735126811754445 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.5028901734104047, "acc_stderr": 0.02691864538323901, "acc_norm": 0.5028901734104047, "acc_norm_stderr": 0.02691864538323901 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.2558659217877095, "acc_stderr": 0.014593620923210756, "acc_norm": 0.2558659217877095, "acc_norm_stderr": 0.014593620923210756 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.545751633986928, "acc_stderr": 0.028509807802626592, "acc_norm": 0.545751633986928, "acc_norm_stderr": 0.028509807802626592 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.49517684887459806, "acc_stderr": 0.028396770444111298, "acc_norm": 0.49517684887459806, "acc_norm_stderr": 0.028396770444111298 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.5030864197530864, "acc_stderr": 0.027820214158594377, "acc_norm": 0.5030864197530864, "acc_norm_stderr": 0.027820214158594377 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.3546099290780142, "acc_stderr": 0.028538650028878638, "acc_norm": 0.3546099290780142, "acc_norm_stderr": 0.028538650028878638 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.3324641460234681, "acc_stderr": 0.01203202233226051, "acc_norm": 0.3324641460234681, "acc_norm_stderr": 0.01203202233226051 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.5257352941176471, "acc_stderr": 0.03033257809455502, "acc_norm": 0.5257352941176471, "acc_norm_stderr": 0.03033257809455502 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.46895424836601307, "acc_stderr": 0.020188804456361887, "acc_norm": 0.46895424836601307, "acc_norm_stderr": 0.020188804456361887 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.5636363636363636, "acc_stderr": 0.04750185058907296, "acc_norm": 0.5636363636363636, "acc_norm_stderr": 0.04750185058907296 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.5387755102040817, "acc_stderr": 0.031912820526692774, "acc_norm": 0.5387755102040817, "acc_norm_stderr": 0.031912820526692774 }, "harness|hendrycksTest-sociology|5": { "acc": 0.6318407960199005, "acc_stderr": 0.03410410565495302, "acc_norm": 0.6318407960199005, "acc_norm_stderr": 0.03410410565495302 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-virology|5": { "acc": 0.42771084337349397, "acc_stderr": 0.038515976837185335, "acc_norm": 0.42771084337349397, "acc_norm_stderr": 0.038515976837185335 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.6549707602339181, "acc_stderr": 0.03645981377388806, "acc_norm": 0.6549707602339181, "acc_norm_stderr": 0.03645981377388806 }, "harness|truthfulqa:mc|0": { "mc1": 0.2582619339045288, "mc1_stderr": 0.0153218216884762, "mc2": 0.4053787386286284, "mc2_stderr": 0.013893490031868357 }, "all": { "acc": 0.46685175478824187, "acc_stderr": 0.03531409019484935, "acc_norm": 0.47077526563025673, "acc_norm_stderr": 0.035299387024960424, "mc1": 0.2582619339045288, "mc1_stderr": 0.0153218216884762, "mc2": 0.4053787386286284, "mc2_stderr": 0.013893490031868357 } }, "versions": { "harness|arc:challenge|25": 0, "harness|hellaswag|10": 0, "harness|hendrycksTest-abstract_algebra|5": 1, "harness|hendrycksTest-anatomy|5": 1, "harness|hendrycksTest-astronomy|5": 1, "harness|hendrycksTest-business_ethics|5": 1, "harness|hendrycksTest-clinical_knowledge|5": 1, "harness|hendrycksTest-college_biology|5": 1, "harness|hendrycksTest-college_chemistry|5": 1, "harness|hendrycksTest-college_computer_science|5": 1, "harness|hendrycksTest-college_mathematics|5": 1, "harness|hendrycksTest-college_medicine|5": 1, "harness|hendrycksTest-college_physics|5": 1, "harness|hendrycksTest-computer_security|5": 1, "harness|hendrycksTest-conceptual_physics|5": 1, "harness|hendrycksTest-econometrics|5": 1, "harness|hendrycksTest-electrical_engineering|5": 1, "harness|hendrycksTest-elementary_mathematics|5": 1, "harness|hendrycksTest-formal_logic|5": 1, "harness|hendrycksTest-global_facts|5": 1, "harness|hendrycksTest-high_school_biology|5": 1, "harness|hendrycksTest-high_school_chemistry|5": 1, "harness|hendrycksTest-high_school_computer_science|5": 1, "harness|hendrycksTest-high_school_european_history|5": 1, "harness|hendrycksTest-high_school_geography|5": 1, "harness|hendrycksTest-high_school_government_and_politics|5": 1, "harness|hendrycksTest-high_school_macroeconomics|5": 1, "harness|hendrycksTest-high_school_mathematics|5": 1, "harness|hendrycksTest-high_school_microeconomics|5": 1, "harness|hendrycksTest-high_school_physics|5": 1, "harness|hendrycksTest-high_school_psychology|5": 1, "harness|hendrycksTest-high_school_statistics|5": 1, "harness|hendrycksTest-high_school_us_history|5": 1, "harness|hendrycksTest-high_school_world_history|5": 1, "harness|hendrycksTest-human_aging|5": 1, "harness|hendrycksTest-human_sexuality|5": 1, "harness|hendrycksTest-international_law|5": 1, "harness|hendrycksTest-jurisprudence|5": 1, "harness|hendrycksTest-logical_fallacies|5": 1, "harness|hendrycksTest-machine_learning|5": 1, "harness|hendrycksTest-management|5": 1, "harness|hendrycksTest-marketing|5": 1, "harness|hendrycksTest-medical_genetics|5": 1, "harness|hendrycksTest-miscellaneous|5": 1, "harness|hendrycksTest-moral_disputes|5": 1, "harness|hendrycksTest-moral_scenarios|5": 1, "harness|hendrycksTest-nutrition|5": 1, "harness|hendrycksTest-philosophy|5": 1, "harness|hendrycksTest-prehistory|5": 1, "harness|hendrycksTest-professional_accounting|5": 1, "harness|hendrycksTest-professional_law|5": 1, "harness|hendrycksTest-professional_medicine|5": 1, "harness|hendrycksTest-professional_psychology|5": 1, "harness|hendrycksTest-public_relations|5": 1, "harness|hendrycksTest-security_studies|5": 1, "harness|hendrycksTest-sociology|5": 1, "harness|hendrycksTest-us_foreign_policy|5": 1, "harness|hendrycksTest-virology|5": 1, "harness|hendrycksTest-world_religions|5": 1, "harness|truthfulqa:mc|0": 1, "all": 0 }, "config_general": { "model_name": "chaoyi-wu/MedLLaMA_13B", "model_sha": "893557ef32f98cd01deb1c5d063be6d640ffa657", "model_dtype": "torch.float16", "lighteval_sha": "03c2fad20ff7f5334c33cfee459024b8d7e4a109", "num_few_shot_default": 0, "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null }, "config_tasks": { "harness|arc:challenge": "LM Harness task", "harness|hellaswag": "LM Harness task", "harness|hendrycksTest-abstract_algebra": "LM Harness task", "harness|hendrycksTest-anatomy": "LM Harness task", "harness|hendrycksTest-astronomy": "LM Harness task", "harness|hendrycksTest-business_ethics": "LM Harness task", "harness|hendrycksTest-clinical_knowledge": "LM Harness task", "harness|hendrycksTest-college_biology": "LM Harness task", "harness|hendrycksTest-college_chemistry": "LM Harness task", "harness|hendrycksTest-college_computer_science": "LM Harness task", "harness|hendrycksTest-college_mathematics": "LM Harness task", "harness|hendrycksTest-college_medicine": "LM Harness task", "harness|hendrycksTest-college_physics": "LM Harness task", "harness|hendrycksTest-computer_security": "LM Harness task", "harness|hendrycksTest-conceptual_physics": "LM Harness task", "harness|hendrycksTest-econometrics": "LM Harness task", "harness|hendrycksTest-electrical_engineering": "LM Harness task", "harness|hendrycksTest-elementary_mathematics": "LM Harness task", "harness|hendrycksTest-formal_logic": "LM Harness task", "harness|hendrycksTest-global_facts": "LM Harness task", "harness|hendrycksTest-high_school_biology": "LM Harness task", "harness|hendrycksTest-high_school_chemistry": "LM Harness task", "harness|hendrycksTest-high_school_computer_science": "LM Harness task", "harness|hendrycksTest-high_school_european_history": "LM Harness task", "harness|hendrycksTest-high_school_geography": "LM Harness task", "harness|hendrycksTest-high_school_government_and_politics": "LM Harness task", "harness|hendrycksTest-high_school_macroeconomics": "LM Harness task", "harness|hendrycksTest-high_school_mathematics": "LM Harness task", "harness|hendrycksTest-high_school_microeconomics": "LM Harness task", "harness|hendrycksTest-high_school_physics": "LM Harness task", "harness|hendrycksTest-high_school_psychology": "LM Harness task", "harness|hendrycksTest-high_school_statistics": "LM Harness task", "harness|hendrycksTest-high_school_us_history": "LM Harness task", "harness|hendrycksTest-high_school_world_history": "LM Harness task", "harness|hendrycksTest-human_aging": "LM Harness task", "harness|hendrycksTest-human_sexuality": "LM Harness task", "harness|hendrycksTest-international_law": "LM Harness task", "harness|hendrycksTest-jurisprudence": "LM Harness task", "harness|hendrycksTest-logical_fallacies": "LM Harness task", "harness|hendrycksTest-machine_learning": "LM Harness task", "harness|hendrycksTest-management": "LM Harness task", "harness|hendrycksTest-marketing": "LM Harness task", "harness|hendrycksTest-medical_genetics": "LM Harness task", "harness|hendrycksTest-miscellaneous": "LM Harness task", "harness|hendrycksTest-moral_disputes": "LM Harness task", "harness|hendrycksTest-moral_scenarios": "LM Harness task", "harness|hendrycksTest-nutrition": "LM Harness task", "harness|hendrycksTest-philosophy": "LM Harness task", "harness|hendrycksTest-prehistory": "LM Harness task", "harness|hendrycksTest-professional_accounting": "LM Harness task", "harness|hendrycksTest-professional_law": "LM Harness task", "harness|hendrycksTest-professional_medicine": "LM Harness task", "harness|hendrycksTest-professional_psychology": "LM Harness task", "harness|hendrycksTest-public_relations": "LM Harness task", "harness|hendrycksTest-security_studies": "LM Harness task", "harness|hendrycksTest-sociology": "LM Harness task", "harness|hendrycksTest-us_foreign_policy": "LM Harness task", "harness|hendrycksTest-virology": "LM Harness task", "harness|hendrycksTest-world_religions": "LM Harness task", "harness|truthfulqa:mc": "LM Harness task" }, "summary_tasks": { "harness|arc:challenge|25": { "hashes": { "hash_examples": "17b0cae357c0259e", "hash_full_prompts": "045cbb916e5145c6", "hash_input_tokens": "2b0e07d4cdd3b0fe", "hash_cont_tokens": "52204555b6e39a6e" }, "truncated": 0, "non-truncated": 4687, "padded": 4687, "non-padded": 0, "effective_few_shots": 25.0, "num_truncated_few_shots": 0 }, "harness|hellaswag|10": { "hashes": { "hash_examples": "e1768ecb99d7ecf0", "hash_full_prompts": "0b4c16983130f84f", "hash_input_tokens": "578edd77107cb2c3", "hash_cont_tokens": "25c49737526d9f80" }, "truncated": 0, "non-truncated": 40168, "padded": 40113, "non-padded": 55, "effective_few_shots": 10.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-abstract_algebra|5": { "hashes": { "hash_examples": "280f9f325b40559a", "hash_full_prompts": "2f776a367d23aea2", "hash_input_tokens": "6a95a1511f8da075", "hash_cont_tokens": "50421e30bef398f9" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-anatomy|5": { "hashes": { "hash_examples": "2f83a4f1cab4ba18", "hash_full_prompts": "516f74bef25df620", "hash_input_tokens": "24a78edc4d9a93aa", "hash_cont_tokens": "f11971a765cb609f" }, "truncated": 0, "non-truncated": 540, "padded": 540, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-astronomy|5": { "hashes": { "hash_examples": "7d587b908da4d762", "hash_full_prompts": "faf4e80f65de93ca", "hash_input_tokens": "b11106668d6c0974", "hash_cont_tokens": "ebed26cf74a85815" }, "truncated": 0, "non-truncated": 608, "padded": 608, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-business_ethics|5": { "hashes": { "hash_examples": "33e51740670de686", "hash_full_prompts": "db01c3ef8e1479d4", "hash_input_tokens": "10180ba12a075cb0", "hash_cont_tokens": "6898ac348a7ae442" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-clinical_knowledge|5": { "hashes": { "hash_examples": "f3366dbe7eefffa4", "hash_full_prompts": "49654f71d94b65c3", "hash_input_tokens": "73351ef4968750a2", "hash_cont_tokens": "34a058958a45af94" }, "truncated": 0, "non-truncated": 1060, "padded": 1060, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-college_biology|5": { "hashes": { "hash_examples": "ca2b6753a0193e7f", "hash_full_prompts": "2b460b75f1fdfefd", "hash_input_tokens": "a539150af234c668", "hash_cont_tokens": "875cde3af7a0ee14" }, "truncated": 0, "non-truncated": 576, "padded": 576, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-college_chemistry|5": { "hashes": { "hash_examples": "22ff85f1d34f42d1", "hash_full_prompts": "242c9be6da583e95", "hash_input_tokens": "52e12e5a43bcee35", "hash_cont_tokens": "50421e30bef398f9" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-college_computer_science|5": { "hashes": { "hash_examples": "30318289d717a5cf", "hash_full_prompts": "ed2bdb4e87c4b371", "hash_input_tokens": "d1f3721a5659f7ee", "hash_cont_tokens": "da408cb12ab08288" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-college_mathematics|5": { "hashes": { "hash_examples": "4944d1f0b6b5d911", "hash_full_prompts": "770bc4281c973190", "hash_input_tokens": "f2d78f546b5595c2", "hash_cont_tokens": "50421e30bef398f9" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-college_medicine|5": { "hashes": { "hash_examples": "dd69cc33381275af", "hash_full_prompts": "ad2a53e5250ab46e", "hash_input_tokens": "c9cc19179f63d1d6", "hash_cont_tokens": "370a1a0ab68d15cd" }, "truncated": 0, "non-truncated": 692, "padded": 692, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-college_physics|5": { "hashes": { "hash_examples": "875dd26d22655b0d", "hash_full_prompts": "833a0d7b55aed500", "hash_input_tokens": "5046144e67e992e8", "hash_cont_tokens": "f7b8097afc16a47c" }, "truncated": 0, "non-truncated": 408, "padded": 408, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-computer_security|5": { "hashes": { "hash_examples": "006451eedc0ededb", "hash_full_prompts": "94034c97e85d8f46", "hash_input_tokens": "4b14581ba4fc06fc", "hash_cont_tokens": "50421e30bef398f9" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-conceptual_physics|5": { "hashes": { "hash_examples": "8874ece872d2ca4c", "hash_full_prompts": "e40d15a34640d6fa", "hash_input_tokens": "1ee52c413b5b4cc4", "hash_cont_tokens": "aa0e8bc655f2f641" }, "truncated": 0, "non-truncated": 940, "padded": 940, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-econometrics|5": { "hashes": { "hash_examples": "64d3623b0bfaa43f", "hash_full_prompts": "612f340fae41338d", "hash_input_tokens": "2914077c4dd3090a", "hash_cont_tokens": "80dea4d59245cf01" }, "truncated": 0, "non-truncated": 456, "padded": 456, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-electrical_engineering|5": { "hashes": { "hash_examples": "e98f51780c674d7e", "hash_full_prompts": "10275b312d812ae6", "hash_input_tokens": "0f88a874342378de", "hash_cont_tokens": "2425a3f084a591ef" }, "truncated": 0, "non-truncated": 580, "padded": 580, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-elementary_mathematics|5": { "hashes": { "hash_examples": "fc48208a5ac1c0ce", "hash_full_prompts": "5ec274c6c82aca23", "hash_input_tokens": "9889933f1dd02a23", "hash_cont_tokens": "309bef1803097408" }, "truncated": 0, "non-truncated": 1512, "padded": 1512, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-formal_logic|5": { "hashes": { "hash_examples": "5a6525665f63ea72", "hash_full_prompts": "07b92638c4a6b500", "hash_input_tokens": "dc309a94c4bfdd2f", "hash_cont_tokens": "5105a3bd1b39b785" }, "truncated": 0, "non-truncated": 504, "padded": 504, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-global_facts|5": { "hashes": { "hash_examples": "371d70d743b2b89b", "hash_full_prompts": "332fdee50a1921b4", "hash_input_tokens": "0801a0aebec3ba8c", "hash_cont_tokens": "50421e30bef398f9" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_biology|5": { "hashes": { "hash_examples": "a79e1018b1674052", "hash_full_prompts": "e624e26ede922561", "hash_input_tokens": "5bc4aca8831d9c05", "hash_cont_tokens": "205c5deee1581b02" }, "truncated": 0, "non-truncated": 1240, "padded": 1240, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_chemistry|5": { "hashes": { "hash_examples": "44bfc25c389f0e03", "hash_full_prompts": "0e3e5f5d9246482a", "hash_input_tokens": "b92bd6b06fc3464c", "hash_cont_tokens": "272d28867e0ff046" }, "truncated": 0, "non-truncated": 812, "padded": 812, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_computer_science|5": { "hashes": { "hash_examples": "8b8cdb1084f24169", "hash_full_prompts": "c00487e67c1813cc", "hash_input_tokens": "a549346cde8165e9", "hash_cont_tokens": "98b3bf311aa83f0d" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_european_history|5": { "hashes": { "hash_examples": "11cd32d0ef440171", "hash_full_prompts": "318f4513c537c6bf", "hash_input_tokens": "f1f73dd687da18d7", "hash_cont_tokens": "674fc454bdc5ac93" }, "truncated": 660, "non-truncated": 0, "padded": 0, "non-padded": 660, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_geography|5": { "hashes": { "hash_examples": "b60019b9e80b642f", "hash_full_prompts": "ee5789fcc1a81b1e", "hash_input_tokens": "e7e9cf91f9d6a081", "hash_cont_tokens": "03a5012b916274ea" }, "truncated": 0, "non-truncated": 792, "padded": 792, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "hashes": { "hash_examples": "d221ec983d143dc3", "hash_full_prompts": "ac42d888e1ce1155", "hash_input_tokens": "a61a1670f854d9e1", "hash_cont_tokens": "d9e66fc7c702b795" }, "truncated": 0, "non-truncated": 772, "padded": 772, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "hashes": { "hash_examples": "59c2915cacfd3fbb", "hash_full_prompts": "c6bd9d25158abd0e", "hash_input_tokens": "8a77cb7763f28110", "hash_cont_tokens": "c583432ad27fcfe0" }, "truncated": 0, "non-truncated": 1560, "padded": 1560, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_mathematics|5": { "hashes": { "hash_examples": "1f8ac897608de342", "hash_full_prompts": "5d88f41fc2d643a8", "hash_input_tokens": "fcfcfae391f8faa1", "hash_cont_tokens": "d4b1936084c060e0" }, "truncated": 0, "non-truncated": 1080, "padded": 1080, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_microeconomics|5": { "hashes": { "hash_examples": "ead6a0f2f6c83370", "hash_full_prompts": "bfc393381298609e", "hash_input_tokens": "a29454cc1feb23ef", "hash_cont_tokens": "f47f041de50333b9" }, "truncated": 0, "non-truncated": 952, "padded": 952, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_physics|5": { "hashes": { "hash_examples": "c3f2025990afec64", "hash_full_prompts": "fc78b4997e436734", "hash_input_tokens": "b6734a25556d75dc", "hash_cont_tokens": "2bf9921a39e901d9" }, "truncated": 0, "non-truncated": 604, "padded": 604, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_psychology|5": { "hashes": { "hash_examples": "21f8aab618f6d636", "hash_full_prompts": "d5c76aa40b9dbc43", "hash_input_tokens": "5720438e29473426", "hash_cont_tokens": "cab8b16be9576360" }, "truncated": 0, "non-truncated": 2180, "padded": 2180, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_statistics|5": { "hashes": { "hash_examples": "2386a60a11fc5de3", "hash_full_prompts": "4c5c8be5aafac432", "hash_input_tokens": "486321d5858de240", "hash_cont_tokens": "1c34fbe5a59f1ed1" }, "truncated": 0, "non-truncated": 864, "padded": 864, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_us_history|5": { "hashes": { "hash_examples": "74961543be40f04f", "hash_full_prompts": "5d5ca4840131ba21", "hash_input_tokens": "50c9ff438c85a69e", "hash_cont_tokens": "cdd0b3dc06d933e5" }, "truncated": 816, "non-truncated": 0, "padded": 0, "non-padded": 816, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-high_school_world_history|5": { "hashes": { "hash_examples": "2ad2f6b7198b2234", "hash_full_prompts": "11845057459afd72", "hash_input_tokens": "473919e64d1b8c80", "hash_cont_tokens": "ebd714885a59ef55" }, "truncated": 8, "non-truncated": 940, "padded": 940, "non-padded": 8, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-human_aging|5": { "hashes": { "hash_examples": "1a7199dc733e779b", "hash_full_prompts": "756b9096b8eaf892", "hash_input_tokens": "47a65c81fd7ed010", "hash_cont_tokens": "142a4a8a1138a214" }, "truncated": 0, "non-truncated": 892, "padded": 892, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-human_sexuality|5": { "hashes": { "hash_examples": "7acb8fdad97f88a6", "hash_full_prompts": "731a52ff15b8cfdb", "hash_input_tokens": "aedfcd41cbd2fcc9", "hash_cont_tokens": "bc54813e809b796d" }, "truncated": 0, "non-truncated": 524, "padded": 524, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-international_law|5": { "hashes": { "hash_examples": "1300bfd0dfc59114", "hash_full_prompts": "db2aefbff5eec996", "hash_input_tokens": "ed5f2414144d7b72", "hash_cont_tokens": "aac52fa6a519223b" }, "truncated": 0, "non-truncated": 484, "padded": 484, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-jurisprudence|5": { "hashes": { "hash_examples": "083b1e4904c48dc2", "hash_full_prompts": "0f89ee3fe03d6a21", "hash_input_tokens": "692eaacb5b747264", "hash_cont_tokens": "e3a8cd951b6e3469" }, "truncated": 0, "non-truncated": 432, "padded": 432, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-logical_fallacies|5": { "hashes": { "hash_examples": "709128f9926a634c", "hash_full_prompts": "98a04b1f8f841069", "hash_input_tokens": "2cbce4edca937588", "hash_cont_tokens": "697179a0dd47c5c0" }, "truncated": 0, "non-truncated": 652, "padded": 648, "non-padded": 4, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-machine_learning|5": { "hashes": { "hash_examples": "88f22a636029ae47", "hash_full_prompts": "2e1c8d4b1e0cc921", "hash_input_tokens": "c2f38b19bab1aa2c", "hash_cont_tokens": "9b19898e3ecb527f" }, "truncated": 0, "non-truncated": 448, "padded": 448, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-management|5": { "hashes": { "hash_examples": "8c8a1e07a2151dca", "hash_full_prompts": "f51611f514b265b0", "hash_input_tokens": "fde277bc547bc3d8", "hash_cont_tokens": "a01d6d39a83c4597" }, "truncated": 0, "non-truncated": 412, "padded": 412, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-marketing|5": { "hashes": { "hash_examples": "2668953431f91e96", "hash_full_prompts": "77562bef997c7650", "hash_input_tokens": "87b232bbebce39db", "hash_cont_tokens": "6aeaed4d823c98aa" }, "truncated": 0, "non-truncated": 936, "padded": 936, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-medical_genetics|5": { "hashes": { "hash_examples": "9c2dda34a2ea4fd2", "hash_full_prompts": "202139046daa118f", "hash_input_tokens": "58c21af9da3e126e", "hash_cont_tokens": "50421e30bef398f9" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-miscellaneous|5": { "hashes": { "hash_examples": "41adb694024809c2", "hash_full_prompts": "bffec9fc237bcf93", "hash_input_tokens": "d1f5c770d368e9c6", "hash_cont_tokens": "9b0ab02a64603081" }, "truncated": 0, "non-truncated": 3132, "padded": 3132, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-moral_disputes|5": { "hashes": { "hash_examples": "3171c13ba3c594c4", "hash_full_prompts": "170831fc36f1d59e", "hash_input_tokens": "98d6db15a50aaa8e", "hash_cont_tokens": "1e30d7dedc7588c0" }, "truncated": 0, "non-truncated": 1384, "padded": 1354, "non-padded": 30, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-moral_scenarios|5": { "hashes": { "hash_examples": "9873e077e83e0546", "hash_full_prompts": "08f4ceba3131a068", "hash_input_tokens": "2aabd8c7337502f8", "hash_cont_tokens": "ceee291786cbb123" }, "truncated": 0, "non-truncated": 3580, "padded": 3580, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-nutrition|5": { "hashes": { "hash_examples": "7db1d8142ec14323", "hash_full_prompts": "4c0e68e3586cb453", "hash_input_tokens": "17f8c8f2d4a0a9b1", "hash_cont_tokens": "484df4c25a5460bd" }, "truncated": 0, "non-truncated": 1224, "padded": 1224, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-philosophy|5": { "hashes": { "hash_examples": "9b455b7d72811cc8", "hash_full_prompts": "e467f822d8a0d3ff", "hash_input_tokens": "dfc6df491d991966", "hash_cont_tokens": "9f6ff69d23a48783" }, "truncated": 0, "non-truncated": 1244, "padded": 1244, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-prehistory|5": { "hashes": { "hash_examples": "8be90d0f538f1560", "hash_full_prompts": "152187949bcd0921", "hash_input_tokens": "cffe8139e00da9dd", "hash_cont_tokens": "85a9de6c685b7035" }, "truncated": 0, "non-truncated": 1296, "padded": 1296, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-professional_accounting|5": { "hashes": { "hash_examples": "8d377597916cd07e", "hash_full_prompts": "0eb7345d6144ee0d", "hash_input_tokens": "4a69ed6ee55918fb", "hash_cont_tokens": "ad7b5a040535bdcf" }, "truncated": 0, "non-truncated": 1128, "padded": 1128, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-professional_law|5": { "hashes": { "hash_examples": "cd9dbc52b3c932d6", "hash_full_prompts": "36ac764272bfb182", "hash_input_tokens": "6cc713f12b5890de", "hash_cont_tokens": "2e590029ef41fbcd" }, "truncated": 604, "non-truncated": 5532, "padded": 5524, "non-padded": 612, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-professional_medicine|5": { "hashes": { "hash_examples": "b20e4e816c1e383e", "hash_full_prompts": "7b8d69ea2acaf2f7", "hash_input_tokens": "b4044fc92756c377", "hash_cont_tokens": "0b7b5aaef574dc78" }, "truncated": 0, "non-truncated": 1088, "padded": 1088, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-professional_psychology|5": { "hashes": { "hash_examples": "d45b73b22f9cc039", "hash_full_prompts": "fe8937e9ffc99771", "hash_input_tokens": "b019784da8db089a", "hash_cont_tokens": "63a651778e8d72d2" }, "truncated": 0, "non-truncated": 2448, "padded": 2448, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-public_relations|5": { "hashes": { "hash_examples": "0d25072e1761652a", "hash_full_prompts": "f9adc39cfa9f42ba", "hash_input_tokens": "f47f37c7c9bfc601", "hash_cont_tokens": "841583ab707b25d7" }, "truncated": 0, "non-truncated": 440, "padded": 440, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-security_studies|5": { "hashes": { "hash_examples": "62bb8197e63d60d4", "hash_full_prompts": "869c9c3ae196b7c3", "hash_input_tokens": "4d282718d6142410", "hash_cont_tokens": "9c2c01d3214f66b8" }, "truncated": 0, "non-truncated": 980, "padded": 980, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-sociology|5": { "hashes": { "hash_examples": "e7959df87dea8672", "hash_full_prompts": "1a1fc00e17b3a52a", "hash_input_tokens": "fbc6026e500537bc", "hash_cont_tokens": "c3a3bdfd177eed5b" }, "truncated": 0, "non-truncated": 804, "padded": 804, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-us_foreign_policy|5": { "hashes": { "hash_examples": "4a56a01ddca44dca", "hash_full_prompts": "0c7a7081c71c07b6", "hash_input_tokens": "150dd1ff81ff642e", "hash_cont_tokens": "96353c5969a9028a" }, "truncated": 0, "non-truncated": 400, "padded": 400, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-virology|5": { "hashes": { "hash_examples": "451cc86a8c4f4fe9", "hash_full_prompts": "01e95325d8b738e4", "hash_input_tokens": "fcbac3e735545969", "hash_cont_tokens": "a1f8901800ac9b68" }, "truncated": 0, "non-truncated": 664, "padded": 664, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|hendrycksTest-world_religions|5": { "hashes": { "hash_examples": "3b29cfaf1a81c379", "hash_full_prompts": "e0d79a15083dfdff", "hash_input_tokens": "ffc962a38441ef13", "hash_cont_tokens": "08c0be345e5f1c12" }, "truncated": 0, "non-truncated": 684, "padded": 684, "non-padded": 0, "effective_few_shots": 5.0, "num_truncated_few_shots": 0 }, "harness|truthfulqa:mc|0": { "hashes": { "hash_examples": "23176c0531c7b867", "hash_full_prompts": "36a6d90e75d92d4a", "hash_input_tokens": "9ffb65d225ae550f", "hash_cont_tokens": "16c760a491c6f26e" }, "truncated": 0, "non-truncated": 9996, "padded": 9996, "non-padded": 0, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "d84d18e9a963753d", "hash_full_prompts": "12b540783521a8e6", "hash_input_tokens": "1c61d6705b299f5c", "hash_cont_tokens": "868d6f1055fbd51d" }, "total_evaluation_time_secondes": "3780.4133019447327", "truncated": 2088, "non-truncated": 108931, "padded": 108834, "non-padded": 2185, "num_truncated_few_shots": 0 } }