open-llm-leaderboard-old/details_jpquiroga__Mistral_7B_dare_ties_merge_instruct_open_orca
收藏数据集概述
数据集来源
该数据集是在评估模型 jpquiroga/Mistral_7B_dare_ties_merge_instruct_open_orca 时自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 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" 分割始终指向最新的结果。
- 额外的 "results" 配置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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_jpquiroga__Mistral_7B_dare_ties_merge_instruct_open_orca", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-04-17T12:05:11.517740 的运行。
python { "all": { "acc": 0.6035215302594036, "acc_stderr": 0.033041596843907325, "acc_norm": 0.6082187287537654, "acc_norm_stderr": 0.03371600755584174, "mc1": 0.3843329253365973, "mc1_stderr": 0.017028707301245203, "mc2": 0.5520003498909304, "mc2_stderr": 0.015398180609644712 }, "harness|arc:challenge|25": { "acc": 0.5674061433447098, "acc_stderr": 0.014478005694182526, "acc_norm": 0.60580204778157, "acc_norm_stderr": 0.014280522667467325 }, "harness|hellaswag|10": { "acc": 0.6132244572794264, "acc_stderr": 0.004860162076330982, "acc_norm": 0.8058155745867357, "acc_norm_stderr": 0.003947630921887926 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5333333333333333, "acc_stderr": 0.043097329010363554, "acc_norm": 0.5333333333333333, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6447368421052632, "acc_stderr": 0.03894734487013316, "acc_norm": 0.6447368421052632, "acc_norm_stderr": 0.03894734487013316 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6641509433962264, "acc_stderr": 0.029067220146644826, "acc_norm": 0.6641509433962264, "acc_norm_stderr": 0.029067220146644826 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5953757225433526, "acc_stderr": 0.03742461193887248, "acc_norm": 0.5953757225433526, "acc_norm_stderr": 0.03742461193887248 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201943, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201943 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5106382978723404, "acc_stderr": 0.03267862331014063, "acc_norm": 0.5106382978723404, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.41228070175438597, "acc_stderr": 0.04630653203366595, "acc_norm": 0.41228070175438597, "acc_norm_stderr": 0.04630653203366595 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555497, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555497 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3915343915343915, "acc_stderr": 0.025138091388851105, "acc_norm": 0.3915343915343915, "acc_norm_stderr": 0.025138091388851105 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7129032258064516, "acc_stderr": 0.02573654274559453, "acc_norm": 0.7129032258064516, "acc_norm_stderr": 0.02573654274559453 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4630541871921182, "acc_stderr": 0.035083705204426656, "acc_norm": 0.4630541871921182, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7929292929292929, "acc_stderr": 0.02886977846026704, "acc_norm": 0.7929292929292929, "acc_norm_stderr": 0.02886977846026704 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8290155440414507, "acc_stderr": 0.027171213683164542, "acc_norm": 0.8290155440414507, "acc_norm_stderr": 0.027171213683164542 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5948717948717949, "acc_stderr": 0.024890471769938145, "acc_norm": 0.5948717948717949, "acc_norm_stderr": 0.024890471769938145 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027738969632176088, "acc_norm": 0.29259259259259257, "acc_norm_stderr": 0.027738969632176088 }, "harness|hendrycksTest-high_school_microeconomics|5":
