open-llm-leaderboard-old/details_macadeliccc__SOLAR-math-2x10.7b-v0.2
收藏数据集概述
数据集简介
该数据集是在模型 macadeliccc/SOLAR-math-2x10.7b-v0.2 的评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：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。
- 训练分割："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_macadeliccc__SOLAR-math-2x10.7b-v0.2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-20T21:45:30.967248 运行的最新结果：
python { "all": { "acc": 0.6661893043024104, "acc_stderr": 0.03160529125685929, "acc_norm": 0.6670254575133359, "acc_norm_stderr": 0.0322488639207885, "mc1": 0.5667074663402693, "mc1_stderr": 0.017347024450107485, "mc2": 0.7167756036606316, "mc2_stderr": 0.01508488302488436 }, "harness|arc:challenge|25": { "acc": 0.681740614334471, "acc_stderr": 0.013611993916971453, "acc_norm": 0.7090443686006825, "acc_norm_stderr": 0.013273077865907593 }, "harness|hellaswag|10": { "acc": 0.7092212706632145, "acc_stderr": 0.004531935391507008, "acc_norm": 0.8828918542123083, "acc_norm_stderr": 0.0032089195103099334 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595853, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595853 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7368421052631579, "acc_stderr": 0.03583496176361072, "acc_norm": 0.7368421052631579, "acc_norm_stderr": 0.03583496176361072 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.02872750295788027, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.02872750295788027 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.05021167315686779, "acc_norm": 0.52, "acc_norm_stderr": 0.05021167315686779 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.03614665424180826, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.03614665424180826 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.048580835742663454, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.048580835742663454 }, "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": 0.6340425531914894, "acc_stderr": 0.031489558297455304, "acc_norm": 0.6340425531914894, "acc_norm_stderr": 0.031489558297455304 }, "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": 0.6206896551724138, "acc_stderr": 0.040434618619167466, "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.040434618619167466 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47619047619047616, "acc_stderr": 0.025722097064388535, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.025722097064388535 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4365079365079365, "acc_stderr": 0.04435932892851466, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.04435932892851466 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8161290322580645, "acc_stderr": 0.022037217340267836, "acc_norm": 0.8161290322580645, "acc_norm_stderr": 0.022037217340267836 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8121212121212121, "acc_stderr": 0.03050193405942914, "acc_norm": 0.8121212121212121, "acc_norm_stderr": 0.03050193405942914 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8737373737373737, "acc_stderr": 0.02366435940288023, "acc_norm": 0.8737373737373737, "acc_norm_stderr": 0.02366435940288023 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.02150024957603347, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.02150024957603347 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.658974358974359, "acc_stderr": 0.02403548967633506, "acc_norm": 0.658974358974359, "acc_norm_stderr": 0.02403548967633506 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251976, "acc_norm": 0.35925925925925
