open-llm-leaderboard-old/details_cognitivecomputations__yayi2-30b-llama
收藏数据集概述
数据集摘要
该数据集是在对模型 cognitivecomputations/yayi2-30b-llama 进行评估运行期间自动创建的，评估结果发布在 Open LLM Leaderboard 上。
数据集组成
数据集由 63 个配置组成，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。
额外配置
一个额外的配置 "results" 存储了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 2024-01-10T16:19:39.763701 运行的最新结果：
python { "all": { "acc": 0.6858877636566363, "acc_stderr": 0.03180407855044079, "acc_norm": 0.6971813587179843, "acc_norm_stderr": 0.03247351510237223, "mc1": 0.32802937576499386, "mc1_stderr": 0.016435632932815025, "mc2": 0.4907923298242728, "mc2_stderr": 0.015239259549837077 }, "harness|arc:challenge|25": { "acc": 0.33532423208191126, "acc_stderr": 0.013796182947785564, "acc_norm": 0.35665529010238906, "acc_norm_stderr": 0.013998056902620199 }, "harness|hellaswag|10": { "acc": 0.4402509460266879, "acc_stderr": 0.004954026775425773, "acc_norm": 0.5336586337382991, "acc_norm_stderr": 0.004978462690966908 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7960526315789473, "acc_stderr": 0.032790004063100515, "acc_norm": 0.7960526315789473, "acc_norm_stderr": 0.032790004063100515 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7283018867924528, "acc_stderr": 0.027377706624670713, "acc_norm": 0.7283018867924528, "acc_norm_stderr": 0.027377706624670713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6527777777777778, "acc_stderr": 0.039812405437178615, "acc_norm": 0.6527777777777778, "acc_norm_stderr": 0.039812405437178615 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.59, "acc_stderr": 0.04943110704237101, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7052023121387283, "acc_stderr": 0.034765996075164785, "acc_norm": 0.7052023121387283, "acc_norm_stderr": 0.034765996075164785 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.6764705882352942, "acc_stderr": 0.04655010411319611, "acc_norm": 0.6764705882352942, "acc_norm_stderr": 0.04655010411319611 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036846, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7063829787234043, "acc_stderr": 0.029771642712491227, "acc_norm": 0.7063829787234043, "acc_norm_stderr": 0.029771642712491227 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5964912280701754, "acc_stderr": 0.046151869625837054, "acc_norm": 0.5964912280701754, "acc_norm_stderr": 0.046151869625837054 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7241379310344828, "acc_stderr": 0.037245636197746325, "acc_norm": 0.7241379310344828, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6534391534391535, "acc_stderr": 0.024508777521028424, "acc_norm": 0.6534391534391535, "acc_norm_stderr": 0.024508777521028424 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7161290322580646, "acc_stderr": 0.02564938106302926, "acc_norm": 0.7161290322580646, "acc_norm_stderr": 0.02564938106302926 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6502463054187192, "acc_stderr": 0.03355400904969566, "acc_norm": 0.6502463054187192, "acc_norm_stderr": 0.03355400904969566 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6848484848484848, "acc_stderr": 0.0362773057502241, "acc_norm": 0.6848484848484848, "acc_norm_stderr": 0.0362773057502241 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8434343434343434, "acc_stderr": 0.025890520358141454, "acc_norm": 0.8434343434343434, "acc_norm_stderr": 0.025890520358141454 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7979274611398963, "acc_stderr": 0.028979089794296736, "acc_norm": 0.7979274611398963, "acc_norm_stderr": 0.028979089794296736 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7076923076923077, "acc_stderr": 0.023060438380857733, "acc_norm": 0.7076923076923077, "acc_norm_stderr": 0.023060438380857733 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.5888888888888889, "acc_stderr": 0.02999992350870668, "acc_norm": 0.5888888888888889, "acc_norm_stderr": 0.02999992350870668 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7478991596638656, "acc_stderr": 0.028205545033277726, "acc_norm": 0
