open-llm-leaderboard-old/details_Weyaxi__Helion-4x34B
收藏数据集概述
数据集简介
该数据集是在模型 Weyaxi/Helion-4x34B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，每个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" 分割始终指向最新结果。
结果配置
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。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Weyaxi__Helion-4x34B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-14T13:23:45.843719 运行的最新结果：
python { "all": { "acc": 0.7699592649917206, "acc_stderr": 0.027825032662237632, "acc_norm": 0.7733690955948024, "acc_norm_stderr": 0.028359676428301124, "mc1": 0.4724602203182375, "mc1_stderr": 0.017476930190712187, "mc2": 0.6391431988345577, "mc2_stderr": 0.014739254450901405 }, "harness|arc:challenge|25": { "acc": 0.6646757679180887, "acc_stderr": 0.013796182947785562, "acc_norm": 0.697098976109215, "acc_norm_stderr": 0.013428241573185349 }, "harness|hellaswag|10": { "acc": 0.6577375024895439, "acc_stderr": 0.004734972668299616, "acc_norm": 0.8528181637124079, "acc_norm_stderr": 0.0035356302890914575 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "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": 0.9078947368421053, "acc_stderr": 0.02353268597044349, "acc_norm": 0.9078947368421053, "acc_norm_stderr": 0.02353268597044349 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8150943396226416, "acc_stderr": 0.023893351834464324, "acc_norm": 0.8150943396226416, "acc_norm_stderr": 0.023893351834464324 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9027777777777778, "acc_stderr": 0.02477451625044016, "acc_norm": 0.9027777777777778, "acc_norm_stderr": 0.02477451625044016 }, "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": 0.65, "acc_stderr": 0.04793724854411019, "acc_norm": 0.65, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.48, "acc_stderr": 0.05021167315686779, "acc_norm": 0.48, "acc_norm_stderr": 0.05021167315686779 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7456647398843931, "acc_stderr": 0.0332055644308557, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5686274509803921, "acc_stderr": 0.04928099597287534, "acc_norm": 0.5686274509803921, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.03942772444036624, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7914893617021277, "acc_stderr": 0.02655698211783874, "acc_norm": 0.7914893617021277, "acc_norm_stderr": 0.02655698211783874 }, "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": 0.7862068965517242, "acc_stderr": 0.034165204477475494, "acc_norm": 0.7862068965517242, "acc_norm_stderr": 0.034165204477475494 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6904761904761905, "acc_stderr": 0.023809523809523867, "acc_norm": 0.6904761904761905, "acc_norm_stderr": 0.023809523809523867 }, "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": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9, "acc_stderr": 0.017066403719657255, "acc_norm": 0.9, "acc_norm_stderr": 0.017066403719657255 }, "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": 0.9292929292929293, "acc_stderr": 0.01826310542019949, "acc_norm": 0.9292929292929293, "acc_norm_stderr": 0.01826310542019949 }, "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": 0.823076923076923, "acc_stderr": 0.019348070174396985, "acc_norm": 0.823076923076923, "acc_norm_stderr": 0.019348070174396985 }, "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_microeconomics|
