open-llm-leaderboard-old/details_cognitivecomputations__MegaDolphin-120b
收藏数据集概述
该数据集是在对模型 cognitivecomputations/MegaDolphin-120b 进行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。数据集从一次运行中创建，每个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。
数据集结构
配置
- results: 存储所有运行结果的聚合，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
示例加载
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_cognitivecomputations__MegaDolphin-120b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-21T21:48:58.549252 运行的最新结果：
python { "all": { "acc": 0.6902282983987049, "acc_stderr": 0.03061680900457877, "acc_norm": 0.6956826713561578, "acc_norm_stderr": 0.03120808276540501, "mc1": 0.41370869033047736, "mc1_stderr": 0.017240861812099804, "mc2": 0.592821117756168, "mc2_stderr": 0.015249093012153285 }, "harness|arc:challenge|25": { "acc": 0.643344709897611, "acc_stderr": 0.013998056902620196, "acc_norm": 0.6902730375426621, "acc_norm_stderr": 0.013512058415238361 }, "harness|hellaswag|10": { "acc": 0.7026488747261501, "acc_stderr": 0.004561582009834577, "acc_norm": 0.8780123481378211, "acc_norm_stderr": 0.0032660269509226444 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "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": 0.7828947368421053, "acc_stderr": 0.03355045304882923, "acc_norm": 0.7828947368421053, "acc_norm_stderr": 0.03355045304882923 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7358490566037735, "acc_stderr": 0.0271342916287417, "acc_norm": 0.7358490566037735, "acc_norm_stderr": 0.0271342916287417 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8194444444444444, "acc_stderr": 0.03216600808802268, "acc_norm": 0.8194444444444444, "acc_norm_stderr": 0.03216600808802268 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6936416184971098, "acc_stderr": 0.035149425512674394, "acc_norm": 0.6936416184971098, "acc_norm_stderr": 0.035149425512674394 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.04755129616062946, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.04755129616062946 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816507, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6893617021276596, "acc_stderr": 0.03025123757921317, "acc_norm": 0.6893617021276596, "acc_norm_stderr": 0.03025123757921317 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6620689655172414, "acc_stderr": 0.039417076320648906, "acc_norm": 0.6620689655172414, "acc_norm_stderr": 0.039417076320648906 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47619047619047616, "acc_stderr": 0.025722097064388525, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.025722097064388525 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5238095238095238, "acc_stderr": 0.04467062628403273, "acc_norm": 0.5238095238095238, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8290322580645161, "acc_stderr": 0.02141724293632158, "acc_norm": 0.8290322580645161, "acc_norm_stderr": 0.02141724293632158 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.027998073798781678, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.027998073798781678 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8585858585858586, "acc_stderr": 0.02482590979334335, "acc_norm": 0.8585858585858586, "acc_norm_stderr": 0.02482590979334335 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9119170984455959, "acc_stderr": 0.02045374660160103, "acc_norm": 0.9119170984455959, "acc_norm_stderr": 0.02045374660160103 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7461538461538462, "acc_stderr": 0.022066054378726257, "acc_norm": 0.7461538461538462, "acc_norm_stderr": 0.022066054378726257 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.02831753349606647, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.02831753349606647 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7815126050420168, "acc_stderr": 0.02684151432295894, "acc_norm": 0.7815126050420168, "acc_norm_stderr": 0.02684151432295894 },
