open-llm-leaderboard-old/details_cloudyu__mistral_11B_instruct_v0.1
收藏数据集概述
数据集简介
该数据集是在评估模型 cloudyu/mistral_11B_instruct_v0.1 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
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。"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。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_cloudyu__mistral_11B_instruct_v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-04T19:53:11.814507 运行的最新结果：
python { "all": { "acc": 0.5846956813152795, "acc_stderr": 0.03324659670781286, "acc_norm": 0.5910920316865859, "acc_norm_stderr": 0.033941630368699856, "mc1": 0.45165238678090575, "mc1_stderr": 0.017421480300277643, "mc2": 0.6364340103053324, "mc2_stderr": 0.015132634013081379 }, "harness|arc:challenge|25": { "acc": 0.49829351535836175, "acc_stderr": 0.01461130570505699, "acc_norm": 0.537542662116041, "acc_norm_stderr": 0.014570144495075581 }, "harness|hellaswag|10": { "acc": 0.5569607647878908, "acc_stderr": 0.004957296691391575, "acc_norm": 0.7463652658832902, "acc_norm_stderr": 0.004342017709967959 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.625, "acc_stderr": 0.039397364351956274, "acc_norm": 0.625, "acc_norm_stderr": 0.039397364351956274 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6415094339622641, "acc_stderr": 0.02951470358398176, "acc_norm": 0.6415094339622641, "acc_norm_stderr": 0.02951470358398176 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6944444444444444, "acc_stderr": 0.03852084696008534, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.03852084696008534 }, "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": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6011560693641619, "acc_stderr": 0.037336266553835096, "acc_norm": 0.6011560693641619, "acc_norm_stderr": 0.037336266553835096 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.04724007352383888, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.04724007352383888 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5319148936170213, "acc_stderr": 0.03261936918467383, "acc_norm": 0.5319148936170213, "acc_norm_stderr": 0.03261936918467383 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.42105263157894735, "acc_stderr": 0.046446020912223177, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3783068783068783, "acc_stderr": 0.024976954053155254, "acc_norm": 0.3783068783068783, "acc_norm_stderr": 0.024976954053155254 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.38095238095238093, "acc_stderr": 0.04343525428949097, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.04343525428949097 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6516129032258065, "acc_stderr": 0.027104826328100937, "acc_norm": 0.6516129032258065, "acc_norm_stderr": 0.027104826328100937 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4482758620689655, "acc_stderr": 0.03499113137676744, "acc_norm": 0.4482758620689655, "acc_norm_stderr": 0.03499113137676744 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "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": 0.7222222222222222, "acc_stderr": 0.03191178226713549, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.03191178226713549 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.026499057701397443, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.026499057701397443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5384615384615384, "acc_stderr": 0.025275892070240648, "acc_norm": 0.5384615384615384, "acc_norm_stderr": 0.025275892070240648 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.02803792996911499, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.02803792996911499 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6302521008403361, "acc_stderr":
