open-llm-leaderboard-old/details_ranamhamoud__storytell
收藏数据集概述
该数据集是在模型 ranamhamoud/storytell 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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
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。
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 Open LLM Leaderboard 上的聚合指标。
数据加载示例
以下是加载特定运行详细信息的示例代码：
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ranamhamoud__storytell", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-23T03:17:12.324607 运行的最新结果：
python { "all": { "acc": 0.48009866416786345, "acc_stderr": 0.03433049518839978, "acc_norm": 0.4857462256010946, "acc_norm_stderr": 0.03511465473356836, "mc1": 0.29865361077111385, "mc1_stderr": 0.01602157061376854, "mc2": 0.4456618973141667, "mc2_stderr": 0.014546690512867342 }, "harness|arc:challenge|25": { "acc": 0.5332764505119454, "acc_stderr": 0.014578995859605811, "acc_norm": 0.560580204778157, "acc_norm_stderr": 0.014503747823580122 }, "harness|hellaswag|10": { "acc": 0.6045608444532962, "acc_stderr": 0.004879455474663814, "acc_norm": 0.798546106353316, "acc_norm_stderr": 0.004002665957282748 }, "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": 0.4740740740740741, "acc_stderr": 0.04313531696750575, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.45394736842105265, "acc_stderr": 0.04051646342874143, "acc_norm": 0.45394736842105265, "acc_norm_stderr": 0.04051646342874143 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4830188679245283, "acc_stderr": 0.030755120364119898, "acc_norm": 0.4830188679245283, "acc_norm_stderr": 0.030755120364119898 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4583333333333333, "acc_stderr": 0.04166666666666665, "acc_norm": 0.4583333333333333, "acc_norm_stderr": 0.04166666666666665 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "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": 0.42196531791907516, "acc_stderr": 0.0376574669386515, "acc_norm": 0.42196531791907516, "acc_norm_stderr": 0.0376574669386515 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617746, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617746 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "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": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.47586206896551725, "acc_stderr": 0.041618085035015295, "acc_norm": 0.47586206896551725, "acc_norm_stderr": 0.041618085035015295 }, "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": 0.2857142857142857, "acc_stderr": 0.040406101782088394, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.040406101782088394 }, "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": 0.5161290322580645, "acc_stderr": 0.028429203176724555, "acc_norm": 0.5161290322580645, "acc_norm_stderr": 0.028429203176724555 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.33004926108374383, "acc_stderr": 0.03308530426228257, "acc_norm": 0.33004926108374383, "acc_norm_stderr": 0.03308530426228257 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6363636363636364, "acc_stderr": 0.037563357751878974, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.037563357751878974 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5707070707070707, "acc_stderr": 0.035265527246011986, "acc_norm": 0.5707070707070707, "acc_norm_stderr": 0.035265527246011986 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.694300518134715, "acc_stderr": 0.03324837939758159, "acc_norm": 0.694300518134715, "acc_norm_stderr": 0.03324837939758159 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4358974358974359, "acc_stderr": 0.02514180151117749, "acc_norm": 0.4358974358974359, "acc_norm_stderr": 0.02514180151117749 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945287, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019
