open-llm-leaderboard-old/details_spmurrayzzz__Mistral-Syndicate-7B
收藏数据集概述
数据集简介
该数据集是在评估模型 spmurrayzzz/Mistral-Syndicate-7B 在 Open LLM Leaderboard 上的自动创建的。
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。数据集从2次运行中创建，每个运行可以在每个配置中作为一个特定的分割找到，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_spmurrayzzz__Mistral-Syndicate-7B", "harness_winogrande_5", split="train")
最新结果
这些是最新结果（来自2023-12-30T05:59:03.827358）的示例： python { "all": { "acc": 0.605141246638436, "acc_stderr": 0.03295805344662521, "acc_norm": 0.6090522236898664, "acc_norm_stderr": 0.03362572955811539, "mc1": 0.29253365973072215, "mc1_stderr": 0.015925597445286165, "mc2": 0.43728309890245215, "mc2_stderr": 0.014415164176795973 }, "harness|arc:challenge|25": { "acc": 0.5631399317406144, "acc_stderr": 0.01449442158425652, "acc_norm": 0.6083617747440273, "acc_norm_stderr": 0.014264122124938215 }, "harness|hellaswag|10": { "acc": 0.6285600477992431, "acc_stderr": 0.004822022254886021, "acc_norm": 0.8288189603664609, "acc_norm_stderr": 0.0037589728166275895 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.03842498559395268, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.03842498559395268 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6867924528301886, "acc_stderr": 0.02854479331905533, "acc_norm": 0.6867924528301886, "acc_norm_stderr": 0.02854479331905533 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6944444444444444, "acc_stderr": 0.03852084696008534, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.03852084696008534 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5838150289017341, "acc_stderr": 0.03758517775404947, "acc_norm": 0.5838150289017341, "acc_norm_stderr": 0.03758517775404947 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5276595744680851, "acc_stderr": 0.03263597118409769, "acc_norm": 0.5276595744680851, "acc_norm_stderr": 0.03263597118409769 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878151, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878151 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.36243386243386244, "acc_stderr": 0.024757473902752056, "acc_norm": 0.36243386243386244, "acc_norm_stderr": 0.024757473902752056 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04360314860077459, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7, "acc_stderr": 0.026069362295335137, "acc_norm": 0.7, "acc_norm_stderr": 0.026069362295335137 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.035145285621750094, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.035145285621750094 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.04793724854411018, "acc_norm": 0.65, "acc_norm_stderr": 0.04793724854411018 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7272727272727273, "acc_stderr": 0.0347769116216366, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.0347769116216366 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.030746300742124488, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.030746300742124488 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8341968911917098, "acc_stderr": 0.026839845022314415, "acc_norm": 0.8341968911917098, "acc_norm_stderr": 0.026839845022314415 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6051282051282051, "acc_stderr": 0.024784316942156395, "acc_norm": 0.6051282051282051, "acc_norm_stderr": 0.024784316942156395 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945277, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945277 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.634453781512605, "acc_stderr": 0.0312821770636
