open-llm-leaderboard-old/details_Weyaxi__Cosmosis-3x34B
收藏数据集概述
数据集简介
该数据集是在对模型 Weyaxi/Cosmosis-3x34B 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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，每次运行的详细信息可以在每个配置中找到，以运行的时间戳命名的特定分片形式存储。"train" 分片始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了所有运行结果的汇总，用于计算和显示 Open LLM Leaderboard 上的聚合指标。
数据加载示例
以下是加载运行详细信息的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Weyaxi__Cosmosis-3x34B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-14T11:59:17.025888 运行的最新结果： python { "all": { "acc": 0.7691798340940261, "acc_stderr": 0.027910883477876437, "acc_norm": 0.7725855380923361, "acc_norm_stderr": 0.02844764712553433, "mc1": 0.4663402692778458, "mc1_stderr": 0.017463793867168103, "mc2": 0.6382238408380394, "mc2_stderr": 0.01475552588950266 }, "harness|arc:challenge|25": { "acc": 0.6655290102389079, "acc_stderr": 0.013787460322441377, "acc_norm": 0.697098976109215, "acc_norm_stderr": 0.013428241573185347 }, "harness|hellaswag|10": { "acc": 0.6569408484365664, "acc_stderr": 0.004737608340163403, "acc_norm": 0.851822346146186, "acc_norm_stderr": 0.003545499169558051 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "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": 0.9078947368421053, "acc_stderr": 0.02353268597044349, "acc_norm": 0.9078947368421053, "acc_norm_stderr": 0.02353268597044349 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8150943396226416, "acc_stderr": 0.02389335183446432, "acc_norm": 0.8150943396226416, "acc_norm_stderr": 0.02389335183446432 }, "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": 0.64, "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": 0.6140350877192983, "acc_stderr": 0.04579639422070434, "acc_norm": 0.6140350877192983, "acc_norm_stderr": 0.04579639422070434 }, "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": 0.023577604791655802, "acc_norm": 0.701058201058201, "acc_norm_stderr": 0.023577604791655802 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5873015873015873, "acc_stderr": 0.04403438954768176, "acc_norm": 0.5873015873015873, "acc_norm_stderr": 0.04403438954768176 }, "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": 0.8205128205128205, "acc_stderr": 0.019457390787681803, "acc_norm": 0.8205128205128205, "acc_norm_stderr": 0.019457390787681803 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.43703703703703706, "acc_stderr": 0.030242862397654002, "acc_norm": 0.43703703703703706, "acc_norm_stderr": 0.030242862397
