open-llm-leaderboard-old/details_stanford-oval__Llama-2-7b-WikiChat-fused
收藏数据集概述
数据集摘要
该数据集是在评估模型 stanford-oval/Llama-2-7b-WikiChat-fused 的过程中自动创建的，用于 Open LLM Leaderboard。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63 个配置
- 数据来源：从 1 次运行中创建
- 数据分割：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置："results" 配置存储所有运行结果的聚合，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_stanford-oval__Llama-2-7b-WikiChat-fused", "harness_winogrande_5", split="train")
最新结果
最新结果来自 2024-01-16T05:29:49.524111 运行，包含多个任务的评估指标。以下是部分任务的评估结果：
python { "all": { "acc": 0.3993615462452277, "acc_stderr": 0.03426948672248777, "acc_norm": 0.4047541011703342, "acc_norm_stderr": 0.035187845841979204, "mc1": 0.30966952264381886, "mc1_stderr": 0.01618574435514492, "mc2": 0.46362057203759177, "mc2_stderr": 0.015792473170958256 }, "harness|arc:challenge|25": { "acc": 0.47696245733788395, "acc_stderr": 0.014595873205358262, "acc_norm": 0.5068259385665529, "acc_norm_stderr": 0.014610029151379813 }, "harness|hellaswag|10": { "acc": 0.5690101573391755, "acc_stderr": 0.00494202620027959, "acc_norm": 0.7499502091216889, "acc_norm_stderr": 0.004321564303822422 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.37777777777777777, "acc_stderr": 0.04188307537595853, "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.04188307537595853 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.32894736842105265, "acc_stderr": 0.038234289699266046, "acc_norm": 0.32894736842105265, "acc_norm_stderr": 0.038234289699266046 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4188679245283019, "acc_stderr": 0.030365050829115208, "acc_norm": 0.4188679245283019, "acc_norm_stderr": 0.030365050829115208 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4652777777777778, "acc_stderr": 0.04171115858181618, "acc_norm": 0.4652777777777778, "acc_norm_stderr": 0.04171115858181618 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3179190751445087, "acc_stderr": 0.0355068398916558, "acc_norm": 0.3179190751445087, "acc_norm_stderr": 0.0355068398916558 }, "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": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.37446808510638296, "acc_stderr": 0.03163910665367291, "acc_norm": 0.37446808510638296, "acc_norm_stderr": 0.03163910665367291 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3157894736842105, "acc_stderr": 0.043727482902780064, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.043727482902780064 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.38620689655172413, "acc_stderr": 0.04057324734419035, "acc_norm": 0.38620689655172413, "acc_norm_stderr": 0.04057324734419035 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2724867724867725, "acc_stderr": 0.022930973071633356, "acc_norm": 0.2724867724867725, "acc_norm_stderr": 0.022930973071633356 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2777777777777778, "acc_stderr": 0.040061680838488774, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.040061680838488774 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4290322580645161, "acc_stderr": 0.028156036538233217, "acc_norm": 0.4290322580645161, "acc_norm_stderr": 0.028156036538233217 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.24630541871921183, "acc_stderr": 0.030315099285617715, "acc_norm": 0.24630541871921183, "acc_norm_stderr": 0.030315099285617715 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.41818181818181815, "acc_stderr": 0.03851716319398393, "acc_norm": 0.41818181818181815, "acc_norm_stderr": 0.03851716319398393 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4898989898989899, "acc_stderr": 0.035616254886737454, "acc_norm": 0.4898989898989899, "acc_norm_stderr": 0.035616254886737454 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5492227979274611, "acc_stderr": 0.03590910952235524, "acc_norm": 0.5492227979274611, "acc_norm_stderr": 0.03590910952235524 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4153846153846154, "acc_stderr": 0.02498535492310234, "acc_norm": 0.4153846153846154, "acc_norm_stderr": 0.02498535492310234 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23333333333333334, "acc_stderr": 0.025787874220959316, "acc_norm": 0.23333333333333334, "acc_norm_stderr": 0.025787874220959316 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.42436974789915966,
