open-llm-leaderboard-old/details_InnerI__InnerIAI-chat-7b-grok
收藏数据集概述
该数据集是在对模型 InnerI/InnerIAI-chat-7b-grok 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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。每个运行可以在每个配置中作为一个特定的分割找到，分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 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 2024-03-24T14:54:07.478425 运行的最新结果：
python { "all": { "acc": 0.5353498519757834, "acc_stderr": 0.033750047702372644, "acc_norm": 0.5419252013103447, "acc_norm_stderr": 0.03448883508762743, "mc1": 0.31701346389228885, "mc1_stderr": 0.016289203374403385, "mc2": 0.46558746897101605, "mc2_stderr": 0.014978038075716977 }, "harness|arc:challenge|25": { "acc": 0.4854948805460751, "acc_stderr": 0.014605241081370053, "acc_norm": 0.5213310580204779, "acc_norm_stderr": 0.014598087973127108 }, "harness|hellaswag|10": { "acc": 0.5652260505875324, "acc_stderr": 0.004947141797384127, "acc_norm": 0.7538338976299542, "acc_norm_stderr": 0.0042989606748115765 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5703703703703704, "acc_stderr": 0.04276349494376599, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.04276349494376599 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5526315789473685, "acc_stderr": 0.040463368839782514, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.040463368839782514 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5962264150943396, "acc_stderr": 0.030197611600197946, "acc_norm": 0.5962264150943396, "acc_norm_stderr": 0.030197611600197946 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5625, "acc_stderr": 0.04148415739394154, "acc_norm": 0.5625, "acc_norm_stderr": 0.04148415739394154 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.047937248544110175, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110175 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5317919075144508, "acc_stderr": 0.03804749744364764, "acc_norm": 0.5317919075144508, "acc_norm_stderr": 0.03804749744364764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364395, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364395 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.43829787234042555, "acc_stderr": 0.03243618636108102, "acc_norm": 0.43829787234042555, "acc_norm_stderr": 0.03243618636108102 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3544973544973545, "acc_stderr": 0.024636830602841997, "acc_norm": 0.3544973544973545, "acc_norm_stderr": 0.024636830602841997 }, "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": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6096774193548387, "acc_stderr": 0.027751256636969576, "acc_norm": 0.6096774193548387, "acc_norm_stderr": 0.027751256636969576 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.41379310344827586, "acc_stderr": 0.03465304488406795, "acc_norm": 0.41379310344827586, "acc_norm_stderr": 0.03465304488406795 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.63, "acc_stderr": 0.048523658709391, "acc_norm": 0.63, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7090909090909091, "acc_stderr": 0.03546563019624336, "acc_norm": 0.7090909090909091, "acc_norm_stderr": 0.03546563019624336 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7222222222222222, "acc_stderr": 0.03191178226713546, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.03191178226713546 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7512953367875648, "acc_stderr": 0.031195840877700304, "acc_norm": 0.7512953367875648, "acc_norm_stderr": 0.031195840877700304 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5487179487179488, "acc_stderr": 0.025230381238934837, "acc_norm": 0.5487179487179488, "acc_norm_stderr": 0.025230381238934837 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.0279404571362284, "acc_norm": 0.3, "acc_norm_stderr": 0.0279404571362284 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5294117647058824, "acc_stderr": 0.03242225027115007, "acc_norm": 0.5294117647058824, "acc_norm_stderr": 0.0324222502
