open-llm-leaderboard-old/details_Weyaxi__Astralis-4x34B
收藏数据集概述
数据集来源
该数据集是在评估模型Weyaxi/Astralis-4x34B在Open LLM Leaderboard上的运行过程中自动创建的。
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，用于计算和显示在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_Weyaxi__Astralis-4x34B", "harness_winogrande_5", split="train")
最新结果
以下是最新结果来自2024-01-16T12:46:01.846891的摘要：
python { "all": { "acc": 0.7689655302402937, "acc_stderr": 0.027836439930903466, "acc_norm": 0.7725041323170285, "acc_norm_stderr": 0.028368985132315505, "mc1": 0.4638922888616891, "mc1_stderr": 0.017457800422268622, "mc2": 0.6354665689810353, "mc2_stderr": 0.014745932385231659 }, "harness|arc:challenge|25": { "acc": 0.6638225255972696, "acc_stderr": 0.013804855026205763, "acc_norm": 0.697098976109215, "acc_norm_stderr": 0.013428241573185349 }, "harness|hellaswag|10": { "acc": 0.6563433578968333, "acc_stderr": 0.004739575380508865, "acc_norm": 0.8517227643895638, "acc_norm_stderr": 0.0035464830155691176 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7333333333333333, "acc_stderr": 0.038201699145179055, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.038201699145179055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.9144736842105263, "acc_stderr": 0.02275867713088861, "acc_norm": 0.9144736842105263, "acc_norm_stderr": 0.02275867713088861 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8075471698113208, "acc_stderr": 0.024262979839372277, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372277 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9097222222222222, "acc_stderr": 0.023964965777906935, "acc_norm": 0.9097222222222222, "acc_norm_stderr": 0.023964965777906935 }, "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": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7572254335260116, "acc_stderr": 0.0326926380614177, "acc_norm": 0.7572254335260116, "acc_norm_stderr": 0.0326926380614177 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5588235294117647, "acc_stderr": 0.049406356306056595, "acc_norm": 0.5588235294117647, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036845, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7957446808510639, "acc_stderr": 0.026355158413349417, "acc_norm": 0.7957446808510639, "acc_norm_stderr": 0.026355158413349417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5964912280701754, "acc_stderr": 0.04615186962583707, "acc_norm": 0.5964912280701754, "acc_norm_stderr": 0.04615186962583707 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7862068965517242, "acc_stderr": 0.034165204477475494, "acc_norm": 0.7862068965517242, "acc_norm_stderr": 0.034165204477475494 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.701058201058201, "acc_stderr": 0.023577604791655805, "acc_norm": 0.701058201058201, "acc_norm_stderr": 0.023577604791655805 }, "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": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9064516129032258, "acc_stderr": 0.016565754668270972, "acc_norm": 0.9064516129032258, "acc_norm_stderr": 0.016565754668270972 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6354679802955665, "acc_stderr": 0.0338640574606209, "acc_norm": 0.6354679802955665, "acc_norm_stderr": 0.0338640574606209 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8727272727272727, "acc_stderr": 0.02602465765165619, "acc_norm": 0.8727272727272727, "acc_norm_stderr": 0.02602465765165619 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9343434343434344, "acc_stderr": 0.017646526677233335, "acc_norm": 0.9343434343434344, "acc_norm_stderr": 0.017646526677233335 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9689119170984456, "acc_stderr": 0.012525310625527033, "acc_norm": 0.9689119170984456, "acc_norm_stderr": 0.012525310625527033 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8102564102564103, "acc_stderr": 0.019880165406588803, "acc_norm": 0.8102564102564103, "acc_norm_stderr": 0.019880165406588803 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4444444444444444, "acc_stderr": 0.03029677128606732, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.03029677128606732 }, "harness|hendrycksTest-high_school
