open-llm-leaderboard-old/details_Weyaxi__MetaMath-una-cybertron-v2-bf16-Ties
收藏数据集概述
数据集来源
该数据集是在模型 Weyaxi/MetaMath-una-cybertron-v2-bf16-Ties 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
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 1 次运行中创建，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的 split 形式存储。"train" split 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，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
数据加载示例
以下是加载特定运行详细结果的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Weyaxi__MetaMath-una-cybertron-v2-bf16-Ties", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-09T16:17:55.430276 运行的最新结果： python { "all": { "acc": 0.6301095117404198, "acc_stderr": 0.03256047711626452, "acc_norm": 0.629798681344077, "acc_norm_stderr": 0.03322922327648027, "mc1": 0.3990208078335373, "mc1_stderr": 0.017142825728496767, "mc2": 0.555200832195947, "mc2_stderr": 0.01590653396629896 }, "harness|arc:challenge|25": { "acc": 0.6305460750853242, "acc_stderr": 0.014104578366491887, "acc_norm": 0.6501706484641638, "acc_norm_stderr": 0.013936809212158296 }, "harness|hellaswag|10": { "acc": 0.6700856403106951, "acc_stderr": 0.0046922082796905925, "acc_norm": 0.8367855008962358, "acc_norm_stderr": 0.0036880598312390156 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "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": 0.6776315789473685, "acc_stderr": 0.03803510248351585, "acc_norm": 0.6776315789473685, "acc_norm_stderr": 0.03803510248351585 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880267, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880267 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7083333333333334, "acc_stderr": 0.038009680605548594, "acc_norm": 0.7083333333333334, "acc_norm_stderr": 0.038009680605548594 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.048108401480826346, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.048108401480826346 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.574468085106383, "acc_stderr": 0.03232146916224469, "acc_norm": 0.574468085106383, "acc_norm_stderr": 0.03232146916224469 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "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": 0.3968253968253968, "acc_stderr": 0.025197101074246477, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.025197101074246477 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768176, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768176 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.04793724854411019, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7516129032258064, "acc_stderr": 0.024580028921481003, "acc_norm": 0.7516129032258064, "acc_norm_stderr": 0.024580028921481003 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.03514528562175008, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.0328766675860349, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.0328766675860349 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7676767676767676, "acc_stderr": 0.030088629490217487, "acc_norm": 0.7676767676767676, "acc_norm_stderr": 0.030088629490217487 }, "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": 0.6461538461538462, "acc_stderr": 0.024243783994062153, "acc_norm": 0.6461538461538462, "acc_norm_stderr": 0.024243783994062153 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.028493465091028593, "acc_norm": 0.3222222222222
