open-llm-leaderboard-old/details_maywell__Synatra-RP-Orca-2-7b-v0.1
收藏数据集概述
数据集摘要
该数据集是在评估模型 maywell/Synatra-RP-Orca-2-7b-v0.1 在 Open LLM Leaderboard 上的自动创建的。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
- 配置数量：63个配置
- 运行次数：2次
- 分割方式：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割指向最新结果。
- 额外配置："results" 配置存储所有运行的聚合结果，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_maywell__Synatra-RP-Orca-2-7b-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-07T22:12:28.167170 运行 的最新结果：
python { "all": { "acc": 0.5617788388118229, "acc_stderr": 0.03367703048955596, "acc_norm": 0.565018654271738, "acc_norm_stderr": 0.034368770251827, "mc1": 0.3733170134638923, "mc1_stderr": 0.016932370557570634, "mc2": 0.5254804392398661, "mc2_stderr": 0.015769818879652533 }, "harness|arc:challenge|25": { "acc": 0.5511945392491467, "acc_stderr": 0.014534599585097665, "acc_norm": 0.5742320819112628, "acc_norm_stderr": 0.014449464278868809 }, "harness|hellaswag|10": { "acc": 0.5892252539334794, "acc_stderr": 0.004909689876342047, "acc_norm": 0.7730531766580363, "acc_norm_stderr": 0.004180018992862967 }, "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": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6710526315789473, "acc_stderr": 0.03823428969926603, "acc_norm": 0.6710526315789473, "acc_norm_stderr": 0.03823428969926603 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.62, "acc_stderr": 0.04878317312145632, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6037735849056604, "acc_stderr": 0.030102793781791197, "acc_norm": 0.6037735849056604, "acc_norm_stderr": 0.030102793781791197 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325582, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325582 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.049888765156985884, "acc_norm": 0.44, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5028901734104047, "acc_stderr": 0.038124005659748335, "acc_norm": 0.5028901734104047, "acc_norm_stderr": 0.038124005659748335 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.043898699568087785, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.043898699568087785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4765957446808511, "acc_stderr": 0.032650194750335815, "acc_norm": 0.4765957446808511, "acc_norm_stderr": 0.032650194750335815 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.04462917535336936, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.04462917535336936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5172413793103449, "acc_stderr": 0.04164188720169375, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.04164188720169375 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3306878306878307, "acc_stderr": 0.02422996529842507, "acc_norm": 0.3306878306878307, "acc_norm_stderr": 0.02422996529842507 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6096774193548387, "acc_stderr": 0.027751256636969576, "acc_norm": 0.6096774193548387, "acc_norm_stderr": 0.027751256636969576 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4039408866995074, "acc_stderr": 0.0345245390382204, "acc_norm": 0.4039408866995074, "acc_norm_stderr": 0.0345245390382204 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7333333333333333, "acc_stderr": 0.03453131801885416, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885416 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7424242424242424, "acc_stderr": 0.03115626951964683, "acc_norm": 0.7424242424242424, "acc_norm_stderr": 0.03115626951964683 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8290155440414507, "acc_stderr": 0.027171213683164528, "acc_norm": 0.8290155440414507, "acc_norm_stderr": 0.027171213683164528 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5256410256410257, "acc_stderr": 0.025317649726448666, "acc_norm": 0.5256410256410257, "acc_norm_stderr": 0.025317649726448666 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.02874204090394849, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0
