open-llm-leaderboard-old/details_Aratako__Beyonder-4x7B-random-lora
收藏数据集概述
数据集摘要
该数据集是在评估模型 Aratako/Beyonder-4x7B-random-lora 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
- 数据来源：1 次运行（run）
- 数据分割：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置："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_Aratako__Beyonder-4x7B-random-lora", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-02T20:16:42.836942 运行 的最新结果：
python { "all": { "acc": 0.6524116122888561, "acc_stderr": 0.03209147540288013, "acc_norm": 0.6526918811196057, "acc_norm_stderr": 0.032750650646658046, "mc1": 0.5312117503059975, "mc1_stderr": 0.01746936487457753, "mc2": 0.7049250833848263, "mc2_stderr": 0.014693924406157995 }, "harness|arc:challenge|25": { "acc": 0.6868600682593856, "acc_stderr": 0.013552671543623496, "acc_norm": 0.712457337883959, "acc_norm_stderr": 0.01322671905626613 }, "harness|hellaswag|10": { "acc": 0.6922923720374428, "acc_stderr": 0.004606015773125624, "acc_norm": 0.8740290778729337, "acc_norm_stderr": 0.0033113844981586364 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.04115324610336953, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.04115324610336953 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7094339622641509, "acc_stderr": 0.027943219989337124, "acc_norm": 0.7094339622641509, "acc_norm_stderr": 0.027943219989337124 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7638888888888888, "acc_stderr": 0.03551446610810826, "acc_norm": 0.7638888888888888, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.0325005368436584, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.0325005368436584 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555498, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555498 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4417989417989418, "acc_stderr": 0.025576257061253833, "acc_norm": 0.4417989417989418, "acc_norm_stderr": 0.025576257061253833 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5, "acc_stderr": 0.04472135954999579, "acc_norm": 0.5, "acc_norm_stderr": 0.04472135954999579 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7870967741935484, "acc_stderr": 0.02328766512726855, "acc_norm": 0.7870967741935484, "acc_norm_stderr": 0.02328766512726855 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.03515895551165698, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.03515895551165698 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8131313131313131, "acc_stderr": 0.027772533334218974, "acc_norm": 0.8131313131313131, "acc_norm_stderr": 0.027772533334218974 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8963730569948186, "acc_stderr": 0.02199531196364424, "acc_norm": 0.8963730569948186, "acc_norm_stderr": 0.02199531196364424 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402538, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402538 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027738969632176085, "acc_norm": 0.29259259259259257, "acc_norm_stderr": 0.0277389696321760
