open-llm-leaderboard-old/details_perlthoughts__Starling-LM-alpha-8x7B-MoE
收藏数据集概述
该数据集是在评估模型 perlthoughts/Starling-LM-alpha-8x7B-MoE 的过程中自动创建的，用于 Open LLM Leaderboard。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
- 配置数量：63 个配置
- 数据来源：从 1 次运行中创建
- 数据分割：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割指向最新结果。
- 额外配置："results" 配置存储所有运行的聚合结果，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_perlthoughts__Starling-LM-alpha-8x7B-MoE", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-16T21:04:03.066898 运行的最新结果：
python { "all": { "acc": 0.6485827629012115, "acc_stderr": 0.03189932261733175, "acc_norm": 0.6500544215634738, "acc_norm_stderr": 0.032542506459412, "mc1": 0.3047735618115055, "mc1_stderr": 0.01611412415688245, "mc2": 0.4639249177352108, "mc2_stderr": 0.015154559507326514 }, "harness|arc:challenge|25": { "acc": 0.5998293515358362, "acc_stderr": 0.014317197787809172, "acc_norm": 0.636518771331058, "acc_norm_stderr": 0.014056207319068283 }, "harness|hellaswag|10": { "acc": 0.6655048795060745, "acc_stderr": 0.004708494114574018, "acc_norm": 0.8490340569607648, "acc_norm_stderr": 0.0035728399695219874 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6867924528301886, "acc_stderr": 0.028544793319055326, "acc_norm": 0.6867924528301886, "acc_norm_stderr": 0.028544793319055326 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7638888888888888, "acc_stderr": 0.03551446610810826, "acc_norm": 0.7638888888888888, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "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": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.03614665424180826, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.03614665424180826 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768079, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.032500536843658404, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.032500536843658404 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370332, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370332 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.40476190476190477, "acc_stderr": 0.025279850397404904, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.025279850397404904 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5238095238095238, "acc_stderr": 0.04467062628403273, "acc_norm": 0.5238095238095238, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7903225806451613, "acc_stderr": 0.023157879349083525, "acc_norm": 0.7903225806451613, "acc_norm_stderr": 0.023157879349083525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.46798029556650245, "acc_stderr": 0.035107665979592154, "acc_norm": 0.46798029556650245, "acc_norm_stderr": 0.035107665979592154 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7636363636363637, "acc_stderr": 0.03317505930009181, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.03317505930009181 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.028606204289229865, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229865 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.02098685459328974, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.02098685459328974 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.676923076923077, "acc_stderr": 0.02371088850197057, "acc_norm": 0.676923076923077, "acc_norm_stderr": 0.02371088850197057 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.028493465091028593, "acc_norm": 0.32222222222222224, "acc_norm_stderr": 0.028493465091028593 }, "harness|hendrycksTest-high_school_microeconomics|
