open-llm-leaderboard-old/details_cognitivecomputations__dolphin-2.2-yi-34b-200k
收藏数据集概述
数据集简介
该数据集是在模型cognitivecomputations/dolphin-2.2-yi-34b-200k的评估运行期间自动创建的，用于Open LLM Leaderboard。
数据集组成
数据集包含63个配置，每个配置对应一个评估任务。数据集从2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_cognitivecomputations__dolphin-2.2-yi-34b-200k", "harness_winogrande_5", split="train")
最新结果
以下是2023-12-30T04:55:41.011890运行的最新结果：
python { "all": { "acc": 0.5429897039109348, "acc_stderr": 0.034024777660715086, "acc_norm": 0.5533854375327871, "acc_norm_stderr": 0.034866231322601235, "mc1": 0.27906976744186046, "mc1_stderr": 0.015702107090627904, "mc2": 0.45933703025376155, "mc2_stderr": 0.01568029542861706 }, "harness|arc:challenge|25": { "acc": 0.38822525597269625, "acc_stderr": 0.014241614207414037, "acc_norm": 0.4206484641638225, "acc_norm_stderr": 0.014426211252508403 }, "harness|hellaswag|10": { "acc": 0.5128460466042621, "acc_stderr": 0.004988134303021787, "acc_norm": 0.6813383788090022, "acc_norm_stderr": 0.004650052150094422 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6118421052631579, "acc_stderr": 0.03965842097512744, "acc_norm": 0.6118421052631579, "acc_norm_stderr": 0.03965842097512744 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6226415094339622, "acc_stderr": 0.02983280811479601, "acc_norm": 0.6226415094339622, "acc_norm_stderr": 0.02983280811479601 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6180555555555556, "acc_stderr": 0.040629907841466674, "acc_norm": 0.6180555555555556, "acc_norm_stderr": 0.040629907841466674 }, "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": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5260115606936416, "acc_stderr": 0.03807301726504514, "acc_norm": 0.5260115606936416, "acc_norm_stderr": 0.03807301726504514 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.04878608714466996, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.04878608714466996 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5063829787234042, "acc_stderr": 0.03268335899936336, "acc_norm": 0.5063829787234042, "acc_norm_stderr": 0.03268335899936336 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.046151869625837026, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.046151869625837026 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.35714285714285715, "acc_stderr": 0.024677862841332783, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.024677862841332783 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.29365079365079366, "acc_stderr": 0.040735243221471255, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.040735243221471255 }, "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": 0.6741935483870968, "acc_stderr": 0.0266620105785671, "acc_norm": 0.6741935483870968, "acc_norm_stderr": 0.0266620105785671 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39901477832512317, "acc_stderr": 0.034454876862647144, "acc_norm": 0.39901477832512317, "acc_norm_stderr": 0.034454876862647144 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7272727272727273, "acc_stderr": 0.03477691162163659, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.03477691162163659 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7474747474747475, "acc_stderr": 0.030954055470365897, "acc_norm": 0.7474747474747475, "acc_norm_stderr": 0.030954055470365897 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7616580310880829, "acc_stderr": 0.030748905363909895, "acc_norm": 0.7616580310880829, "acc_norm_stderr": 0.030748905363909895 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.47435897435897434, "acc_stderr": 0.025317649726448656, "acc_norm": 0.47435897435897434, "acc_norm_stderr": 0.025317649726448656 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.027940457136228412, "acc_norm": 0.3, "acc_norm_stderr": 0.02794045713622
