open-llm-leaderboard-old/details_Undi95__Mistral-11B-TestBench10
收藏数据集概述
数据集简介
该数据集是在对模型 Undi95/Mistral-11B-TestBench10 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集由 61 个配置组成，每个配置对应一个评估任务。数据集是从 1 次运行中创建的，每次运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。"train" 拆分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。
最新结果
以下是 2023-10-11T20:32:37.017457 运行的最新结果：
python { "all": { "acc": 0.6389303587566675, "acc_stderr": 0.033080650268054235, "acc_norm": 0.6424809348544399, "acc_norm_stderr": 0.033059008030264514, "mc1": 0.39412484700122397, "mc1_stderr": 0.017106588140700322, "mc2": 0.5556543619352063, "mc2_stderr": 0.015507002997196854 }, "harness|arc:challenge|25": { "acc": 0.6220136518771331, "acc_stderr": 0.014169664520303098, "acc_norm": 0.6424914675767918, "acc_norm_stderr": 0.014005494275916576 }, "harness|hellaswag|10": { "acc": 0.6533559051981677, "acc_stderr": 0.004749286071559565, "acc_norm": 0.8423620792670783, "acc_norm_stderr": 0.003636564286352674 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595852, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595852 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6710526315789473, "acc_stderr": 0.038234289699266046, "acc_norm": 0.6710526315789473, "acc_norm_stderr": 0.038234289699266046 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7056603773584905, "acc_stderr": 0.02804918631569525, "acc_norm": 0.7056603773584905, "acc_norm_stderr": 0.02804918631569525 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "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": 0.6705202312138728, "acc_stderr": 0.03583901754736412, "acc_norm": 0.6705202312138728, "acc_norm_stderr": 0.03583901754736412 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.048971049527263666, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5446808510638298, "acc_stderr": 0.03255525359340354, "acc_norm": 0.5446808510638298, "acc_norm_stderr": 0.03255525359340354 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878152, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878152 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3941798941798942, "acc_stderr": 0.02516798233389414, "acc_norm": 0.3941798941798942, "acc_norm_stderr": 0.02516798233389414 }, "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": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7451612903225806, "acc_stderr": 0.024790118459332208, "acc_norm": 0.7451612903225806, "acc_norm_stderr": 0.024790118459332208 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7636363636363637, "acc_stderr": 0.03317505930009182, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.03317505930009182 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229872, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229872 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8860103626943006, "acc_stderr": 0.022935144053919443, "acc_norm": 0.8860103626943006, "acc_norm_stderr": 0.022935144053919443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6820512820512821, "acc_stderr": 0.02361088430892786, "acc_norm": 0.6820512820512821, "acc_norm_stderr": 0.02361088430892786 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.36666666666666664, "acc_stderr": 0.029381620726465073, "acc_norm": 0.36666666666666664, "acc_norm_stderr": 0.029381620726465073 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6512605042016807, "
