open-llm-leaderboard-old/details_mobidic__solar-10b-platypus-lora
收藏数据集概述
该数据集是在评估模型 mobidic/solar-10b-platypus-lora 在 Open LLM Leaderboard 上的运行过程中自动创建的。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
- 创建来源：从 1 次运行中创建
- 数据分割：每个配置包含特定运行的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 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在 Open LLM Leaderboard 上。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_mobidic__solar-10b-platypus-lora", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-07T01:04:36.436607 运行的最新结果：
python { "all": { "acc": 0.630557875270941, "acc_stderr": 0.03237223596485076, "acc_norm": 0.6356427832178771, "acc_norm_stderr": 0.03303884410407219, "mc1": 0.36107711138310894, "mc1_stderr": 0.016814312844836886, "mc2": 0.5269712022738704, "mc2_stderr": 0.014945131429082577 }, "harness|arc:challenge|25": { "acc": 0.5793515358361775, "acc_stderr": 0.0144262112525084, "acc_norm": 0.6220136518771331, "acc_norm_stderr": 0.014169664520303098 }, "harness|hellaswag|10": { "acc": 0.6422027484564827, "acc_stderr": 0.0047837237982864995, "acc_norm": 0.8415654252141008, "acc_norm_stderr": 0.003644017383711595 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.049020713000019756, "acc_norm": 0.39, "acc_norm_stderr": 0.049020713000019756 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.562962962962963, "acc_stderr": 0.04284958639753401, "acc_norm": 0.562962962962963, "acc_norm_stderr": 0.04284958639753401 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.038424985593952694, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.038424985593952694 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.028637235639800886, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.028637235639800886 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6358381502890174, "acc_stderr": 0.03669072477416906, "acc_norm": 0.6358381502890174, "acc_norm_stderr": 0.03669072477416906 }, "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": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.032500536843658404, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.032500536843658404 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.04685473041907789, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.04685473041907789 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4444444444444444, "acc_stderr": 0.025591857761382175, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.025591857761382175 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "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": 0.7612903225806451, "acc_stderr": 0.024251071262208837, "acc_norm": 0.7612903225806451, "acc_norm_stderr": 0.024251071262208837 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43842364532019706, "acc_stderr": 0.03491207857486518, "acc_norm": 0.43842364532019706, "acc_norm_stderr": 0.03491207857486518 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8242424242424242, "acc_stderr": 0.02972094300622445, "acc_norm": 0.8242424242424242, "acc_norm_stderr": 0.02972094300622445 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8434343434343434, "acc_stderr": 0.025890520358141454, "acc_norm": 0.8434343434343434, "acc_norm_stderr": 0.025890520358141454 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.02338193534812143, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.02338193534812143 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6333333333333333, "acc_stderr": 0.024433016466052452, "acc_norm": 0.6333333333333333, "acc_norm_stderr": 0.024433016466052452 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32592592592592595, "acc_stderr": 0.028578348365473082, "acc_norm": 0.32592592592592595, "
