open-llm-leaderboard-old/details_mergedlm__zephyrnotus-11b-alpha
收藏数据集概述
数据集摘要
该数据集是在对模型 mergedlm/zephyrnotus-11b-alpha 进行评估运行期间自动创建的。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，每次运行的详细信息可以在每个配置中以特定分割形式找到，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。此外，一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
最新结果
以下是 2023-12-04T18:58:32.292259 运行的最新结果：
python { "all": { "acc": 0.6022156893041962, "acc_stderr": 0.03336144237047965, "acc_norm": 0.6105212360689912, "acc_norm_stderr": 0.03409373060010593, "mc1": 0.401468788249694, "mc1_stderr": 0.017160273901693654, "mc2": 0.5721680885718956, "mc2_stderr": 0.015636158796667236 }, "harness|arc:challenge|25": { "acc": 0.5853242320819113, "acc_stderr": 0.014397070564409174, "acc_norm": 0.613481228668942, "acc_norm_stderr": 0.014230084761910478 }, "harness|hellaswag|10": { "acc": 0.6352320254929297, "acc_stderr": 0.004803812631994954, "acc_norm": 0.8280223063134834, "acc_norm_stderr": 0.003765898364938865 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.562962962962963, "acc_stderr": 0.04284958639753401, "acc_norm": 0.562962962962963, "acc_norm_stderr": 0.04284958639753401 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6052631578947368, "acc_stderr": 0.039777499346220734, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.039777499346220734 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.660377358490566, "acc_stderr": 0.029146904747798335, "acc_norm": 0.660377358490566, "acc_norm_stderr": 0.029146904747798335 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6127167630057804, "acc_stderr": 0.03714325906302065, "acc_norm": 0.6127167630057804, "acc_norm_stderr": 0.03714325906302065 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.048971049527263666, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5361702127659574, "acc_stderr": 0.03260038511835772, "acc_norm": 0.5361702127659574, "acc_norm_stderr": 0.03260038511835772 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.04697085136647863, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.04697085136647863 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.04161808503501531, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.04161808503501531 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3915343915343915, "acc_stderr": 0.025138091388851116, "acc_norm": 0.3915343915343915, "acc_norm_stderr": 0.025138091388851116 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7741935483870968, "acc_stderr": 0.023785577884181015, "acc_norm": 0.7741935483870968, "acc_norm_stderr": 0.023785577884181015 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4876847290640394, "acc_stderr": 0.035169204442208966, "acc_norm": 0.4876847290640394, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.703030303030303, "acc_stderr": 0.03567969772268049, "acc_norm": 0.703030303030303, "acc_norm_stderr": 0.03567969772268049 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7474747474747475, "acc_stderr": 0.030954055470365907, "acc_norm": 0.7474747474747475, "acc_norm_stderr": 0.030954055470365907 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8186528497409327, "acc_stderr": 0.02780703236068609, "acc_norm": 0.8186528497409327, "acc_norm_stderr": 0.02780703236068609 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6153846153846154, "acc_stderr": 0.024666744915187208, "acc_norm": 0.6153846153846154, "acc_norm_stderr": 0.024666744915187208 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524572, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.028661201116524572 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6428571428571429, "acc_stderr": 0.031124619309328177, "acc_norm": 0.6428571428571429, "acc_norm_stderr":
