open-llm-leaderboard-old/details_DreadPoor__Kindred-7B-slerp
收藏数据集概述
数据集来源
该数据集是在模型DreadPoor/Kindred-7B-slerp在Open LLM Leaderboard上的评估运行期间自动创建的。
数据集组成
数据集包含63个配置，每个配置对应一个评估任务。数据集从1次运行中创建，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。"train"分割始终指向最新的结果。
结果配置
一个额外的配置"results"存储所有运行的聚合结果，用于计算和显示Open LLM Leaderboard上的聚合指标。
最新结果
以下是2024-03-06T04:34:27.779341运行的最新结果：
python { "all": { "acc": 0.652918276624435, "acc_stderr": 0.03217962561512012, "acc_norm": 0.6527130051694514, "acc_norm_stderr": 0.0328482909372264, "mc1": 0.5250917992656059, "mc1_stderr": 0.017481446804104014, "mc2": 0.6812302607383641, "mc2_stderr": 0.014858561443304524 }, "harness|arc:challenge|25": { "acc": 0.6800341296928327, "acc_stderr": 0.01363134580701619, "acc_norm": 0.7175767918088737, "acc_norm_stderr": 0.013155456884097225 }, "harness|hellaswag|10": { "acc": 0.7001593308105954, "acc_stderr": 0.004572515919210697, "acc_norm": 0.8778131846245768, "acc_norm_stderr": 0.0032683212609136295 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7169811320754716, "acc_stderr": 0.027724236492700918, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700918 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7847222222222222, "acc_stderr": 0.03437079344106135, "acc_norm": 0.7847222222222222, "acc_norm_stderr": 0.03437079344106135 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.45098039215686275, "acc_stderr": 0.04951218252396262, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.04951218252396262 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932263, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932263 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5872340425531914, "acc_stderr": 0.03218471141400351, "acc_norm": 0.5872340425531914, "acc_norm_stderr": 0.03218471141400351 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5087719298245614, "acc_stderr": 0.047028804320496165, "acc_norm": 0.5087719298245614, "acc_norm_stderr": 0.047028804320496165 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.593103448275862, "acc_stderr": 0.04093793981266236, "acc_norm": 0.593103448275862, "acc_norm_stderr": 0.04093793981266236 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42063492063492064, "acc_stderr": 0.025424835086924003, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.025424835086924003 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.47619047619047616, "acc_stderr": 0.04467062628403273, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7806451612903226, "acc_stderr": 0.023540799358723295, "acc_norm": 0.7806451612903226, "acc_norm_stderr": 0.023540799358723295 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.0328766675860349, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.0328766675860349 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.02860620428922987, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.02860620428922987 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.021500249576033456, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.021500249576033456 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.676923076923077, "acc_stderr": 0.02371088850197057, "acc_norm": 0.676923076923077, "acc_norm_stderr": 0.02371088850197057 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.029116617606083, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.029116617606083 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6932773109243697, "acc_stderr": 0.02995382389188703
