open-llm-leaderboard/details_klosax__open_llama_3b_350bt_preview
收藏数据集概述
数据集简介
该数据集是在评估模型 klosax/open_llama_3b_350bt_preview 的过程中自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集包含 61 个配置，每个配置对应一个评估任务。数据集来源于 1 次运行，每次运行在每个配置中都有特定的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了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_klosax__open_llama_3b_350bt_preview", "harness_truthfulqa_mc_0", split="train")
最新结果
这些是最新结果，来自 2023-07-24T10:25:13.548749 的运行： python { "all": { "acc": 0.27221888756913304, "acc_stderr": 0.03212813724268037, "acc_norm": 0.2751900409341744, "acc_norm_stderr": 0.032129932454657235, "mc1": 0.22031823745410037, "mc1_stderr": 0.01450904517148729, "mc2": 0.35027279444600373, "mc2_stderr": 0.01335009503768823 }, "harness|arc:challenge|25": { "acc": 0.34215017064846415, "acc_stderr": 0.01386415215917728, "acc_norm": 0.3651877133105802, "acc_norm_stderr": 0.014070265519268802 }, "harness|hellaswag|10": { "acc": 0.4563831905994822, "acc_stderr": 0.004970759774676886, "acc_norm": 0.6086436964748058, "acc_norm_stderr": 0.004870563921220623 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2740740740740741, "acc_stderr": 0.03853254836552003, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.03853254836552003 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.23026315789473684, "acc_stderr": 0.03426059424403165, "acc_norm": 0.23026315789473684, "acc_norm_stderr": 0.03426059424403165 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.30566037735849055, "acc_stderr": 0.028353298073322666, "acc_norm": 0.30566037735849055, "acc_norm_stderr": 0.028353298073322666 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.22916666666666666, "acc_stderr": 0.03514697467862388, "acc_norm": 0.22916666666666666, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.22, "acc_stderr": 0.0416333199893227, "acc_norm": 0.22, "acc_norm_stderr": 0.0416333199893227 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.24277456647398843, "acc_stderr": 0.0326926380614177, "acc_norm": 0.24277456647398843, "acc_norm_stderr": 0.0326926380614177 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.14705882352941177, "acc_stderr": 0.03524068951567447, "acc_norm": 0.14705882352941177, "acc_norm_stderr": 0.03524068951567447 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.33191489361702126, "acc_stderr": 0.03078373675774565, "acc_norm": 0.33191489361702126, "acc_norm_stderr": 0.03078373675774565 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.041857744240220554, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.041857744240220554 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2620689655172414, "acc_stderr": 0.03664666337225256, "acc_norm": 0.2620689655172414, "acc_norm_stderr": 0.03664666337225256 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.02241804289111394, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.02241804289111394 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.14285714285714285, "acc_stderr": 0.03129843185743811, "acc_norm": 0.14285714285714285, "acc_norm_stderr": 0.03129843185743811 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.27419354838709675, "acc_stderr": 0.025378139970885196, "acc_norm": 0.27419354838709675, "acc_norm_stderr": 0.025378139970885196 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2955665024630542, "acc_stderr": 0.032104944337514575, "acc_norm": 0.2955665024630542, "acc_norm_stderr": 0.032104944337514575 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.23030303030303031, "acc_stderr": 0.032876667586034886, "acc_norm": 0.23030303030303031, "acc_norm_stderr": 0.032876667586034886 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3383838383838384, "acc_stderr": 0.03371124142626304, "acc_norm": 0.3383838383838384, "acc_norm_stderr": 0.03371124142626304 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.27979274611398963, "acc_stderr": 0.032396370467357036, "acc_norm": 0.27979274611398963, "acc_norm_stderr": 0.032396370467357036 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.26153846153846155, "acc_stderr": 0.022282141204204416, "acc_norm": 0.26153846153846155, "acc_norm_stderr": 0.022282141204204416 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24074074074074073, "acc_stderr": 0.026067159222275798, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.026067159222275798 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.285714285714285
