open-llm-leaderboard-old/details_wenbopan__Faro-Yi-9B
收藏数据集概述
数据集来源
该数据集是在对模型 wenbopan/Faro-Yi-9B 进行评估运行期间自动创建的，评估运行在 Open LLM Leaderboard 上进行。
数据集组成
数据集由 63 个配置组成，每个配置对应一个评估任务。数据集从 1 次运行中创建，每次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。
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 最新结果 的摘要：
python { "all": { "acc": 0.7031416962013707, "acc_stderr": 0.030680865315502705, "acc_norm": 0.7071804818921956, "acc_norm_stderr": 0.031276824574736156, "mc1": 0.3402692778457772, "mc1_stderr": 0.016586304901762557, "mc2": 0.5017234911251813, "mc2_stderr": 0.01516413664590035 }, "harness|arc:challenge|25": { "acc": 0.5793515358361775, "acc_stderr": 0.014426211252508406, "acc_norm": 0.6126279863481229, "acc_norm_stderr": 0.01423587248790987 }, "harness|hellaswag|10": { "acc": 0.5798645688109938, "acc_stderr": 0.00492571700809971, "acc_norm": 0.7694682334196375, "acc_norm_stderr": 0.004203124489037139 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6666666666666666, "acc_stderr": 0.04072314811876837, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7960526315789473, "acc_stderr": 0.0327900040631005, "acc_norm": 0.7960526315789473, "acc_norm_stderr": 0.0327900040631005 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.81, "acc_stderr": 0.03942772444036623, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7433962264150943, "acc_stderr": 0.02688064788905197, "acc_norm": 0.7433962264150943, "acc_norm_stderr": 0.02688064788905197 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8055555555555556, "acc_stderr": 0.033096151770590075, "acc_norm": 0.8055555555555556, "acc_norm_stderr": 0.033096151770590075 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237101, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.45, "acc_stderr": 0.04999999999999999, "acc_norm": 0.45, "acc_norm_stderr": 0.04999999999999999 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7052023121387283, "acc_stderr": 0.03476599607516478, "acc_norm": 0.7052023121387283, "acc_norm_stderr": 0.03476599607516478 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.04940635630605659, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.04940635630605659 }, "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": 0.7276595744680852, "acc_stderr": 0.029101290698386705, "acc_norm": 0.7276595744680852, "acc_norm_stderr": 0.029101290698386705 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.045981880578165414, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6689655172413793, "acc_stderr": 0.039215453124671215, "acc_norm": 0.6689655172413793, "acc_norm_stderr": 0.039215453124671215 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5873015873015873, "acc_stderr": 0.02535574126305525, "acc_norm": 0.5873015873015873, "acc_norm_stderr": 0.02535574126305525 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5714285714285714, "acc_stderr": 0.04426266681379909, "acc_norm": 0.5714285714285714, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8580645161290322, "acc_stderr": 0.01985300367655974, "acc_norm": 0.8580645161290322, "acc_norm_stderr": 0.01985300367655974 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5960591133004927, "acc_stderr": 0.03452453903822032, "acc_norm": 0.5960591133004927, "acc_norm_stderr": 0.03452453903822032 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.84, "acc_stderr": 0.03684529491774708, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774708 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.027998073798781657, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.027998073798781657 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8636363636363636, "acc_stderr": 0.024450155973189835, "acc_norm": 0.8636363636363636, "acc_norm_stderr": 0.024450155973189835 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.917098445595855, "acc_stderr": 0.01989934131572178, "acc_norm": 0.917098445595855, "acc_norm_stderr": 0.01989934131572178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7538461538461538, "acc_stderr": 0.021840866990423077, "acc_norm": 0.7538461538461538, "acc_norm_stderr": 0.021840866990423077 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.45555555555555555, "acc_stderr": 0.03036486250482443, "acc_norm": 0.45555555555555555, "acc_norm_stderr": 0.03036486250482443 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8151260504201681, "acc_stderr": 0.025215992877954
