open-llm-leaderboard-old/details_BFauber__lora_llama2-13b_10e5_r128_a4
收藏数据集概述
数据集简介
该数据集是在模型BFauber/lora_llama2-13b_10e5_r128_a4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
数据集由1次运行创建，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。
结果配置
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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_BFauber__lora_llama2-13b_10e5_r128_a4", "harness_winogrande_5", split="train")
最新结果
以下是最新结果的摘要： python { "all": { "acc": 0.5536824001563057, "acc_stderr": 0.03369978145762168, "acc_norm": 0.5597745031291196, "acc_norm_stderr": 0.03442405976896163, "mc1": 0.26438188494492043, "mc1_stderr": 0.015438211119522512, "mc2": 0.38054701174178024, "mc2_stderr": 0.013756231484196819 }, "harness|arc:challenge|25": { "acc": 0.5588737201365188, "acc_stderr": 0.014509747749064663, "acc_norm": 0.5989761092150171, "acc_norm_stderr": 0.014322255790719869 }, "harness|hellaswag|10": { "acc": 0.616211909978092, "acc_stderr": 0.004853134271547769, "acc_norm": 0.8243377813184625, "acc_norm_stderr": 0.0037975482528516263 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4962962962962963, "acc_stderr": 0.04319223625811331, "acc_norm": 0.4962962962962963, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5460526315789473, "acc_stderr": 0.04051646342874142, "acc_norm": 0.5460526315789473, "acc_norm_stderr": 0.04051646342874142 }, "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": 0.6113207547169811, "acc_stderr": 0.030000485448675986, "acc_norm": 0.6113207547169811, "acc_norm_stderr": 0.030000485448675986 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325583, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325583 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768077, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768077 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5606936416184971, "acc_stderr": 0.03784271932887467, "acc_norm": 0.5606936416184971, "acc_norm_stderr": 0.03784271932887467 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.28431372549019607, "acc_stderr": 0.04488482852329017, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.04488482852329017 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4127659574468085, "acc_stderr": 0.03218471141400352, "acc_norm": 0.4127659574468085, "acc_norm_stderr": 0.03218471141400352 }, "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": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.328042328042328, "acc_stderr": 0.024180497164376907, "acc_norm": 0.328042328042328, "acc_norm_stderr": 0.024180497164376907 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.041905964388711366, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.041905964388711366 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6645161290322581, "acc_stderr": 0.026860206444724345, "acc_norm": 0.6645161290322581, "acc_norm_stderr": 0.026860206444724345 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4729064039408867, "acc_stderr": 0.03512819077876106, "acc_norm": 0.4729064039408867, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "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": 0.6919191919191919, "acc_stderr": 0.032894773300986155, "acc_norm": 0.6919191919191919, "acc_norm_stderr": 0.032894773300986155 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7979274611398963, "acc_stderr": 0.02897908979429673, "acc_norm": 0.7979274611398963, "acc_norm_stderr": 0.02897908979429673 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4948717948717949, "acc_stderr": 0.025349672906838653, "acc_norm": 0.4948717948717949, "acc_norm_stderr": 0.025349672906838653 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.027940457136228416, "acc_norm": 0.3, "acc_norm_stderr": 0.0279404571
