open-llm-leaderboard-old/details_VAGOsolutions__SauerkrautLM-Mixtral-8x7B-Instruct
收藏数据集概述
数据集简介
该数据集是在评估模型 VAGOsolutions/SauerkrautLM-Mixtral-8x7B-Instruct 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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，每次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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_VAGOsolutions__SauerkrautLM-Mixtral-8x7B-Instruct", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要：
python { "all": { "acc": 0.7125714200175716, "acc_stderr": 0.030241466212459073, "acc_norm": 0.7162852145239326, "acc_norm_stderr": 0.03082439912507631, "mc1": 0.5067319461444308, "mc1_stderr": 0.017501914492655396, "mc2": 0.6571120138409167, "mc2_stderr": 0.015075157168756756 }, "harness|arc:challenge|25": { "acc": 0.6783276450511946, "acc_stderr": 0.013650488084494162, "acc_norm": 0.7047781569965871, "acc_norm_stderr": 0.01332975029338232 }, "harness|hellaswag|10": { "acc": 0.6898028281218881, "acc_stderr": 0.004616288245259752, "acc_norm": 0.8775144393547102, "acc_norm_stderr": 0.0032717574453291543 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.674074074074074, "acc_stderr": 0.040491220417025055, "acc_norm": 0.674074074074074, "acc_norm_stderr": 0.040491220417025055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7894736842105263, "acc_stderr": 0.03317672787533157, "acc_norm": 0.7894736842105263, "acc_norm_stderr": 0.03317672787533157 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7735849056603774, "acc_stderr": 0.02575755989310673, "acc_norm": 0.7735849056603774, "acc_norm_stderr": 0.02575755989310673 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8263888888888888, "acc_stderr": 0.03167473383795718, "acc_norm": 0.8263888888888888, "acc_norm_stderr": 0.03167473383795718 }, "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": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "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": 0.7630057803468208, "acc_stderr": 0.032424147574830975, "acc_norm": 0.7630057803468208, "acc_norm_stderr": 0.032424147574830975 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "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": 0.6638297872340425, "acc_stderr": 0.030881618520676942, "acc_norm": 0.6638297872340425, "acc_norm_stderr": 0.030881618520676942 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.04598188057816542, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.04598188057816542 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6551724137931034, "acc_stderr": 0.03960933549451208, "acc_norm": 0.6551724137931034, "acc_norm_stderr": 0.03960933549451208 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.48148148148148145, "acc_stderr": 0.025733641991838987, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.025733641991838987 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5158730158730159, "acc_stderr": 0.044698818540726076, "acc_norm": 0.5158730158730159, "acc_norm_stderr": 0.044698818540726076 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8548387096774194, "acc_stderr": 0.02003956362805329, "acc_norm": 0.8548387096774194, "acc_norm_stderr": 0.02003956362805329 }, "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": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.793939393939394, "acc_stderr": 0.03158415324047709, "acc_norm": 0.793939393939394, "acc_norm_stderr": 0.03158415324047709 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8686868686868687, "acc_stderr": 0.024063156416822516, "acc_norm": 0.8686868686868687, "acc_norm_stderr": 0.024063156416822516 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9585492227979274, "acc_stderr": 0.01438543285747646, "acc_norm": 0.9585492227979274, "acc_norm_stderr": 0.01438543285747646 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7102564102564103, "acc_stderr": 0.023000628243687964, "acc_norm": 0.7102564102564103, "acc_norm_stderr": 0.023000628243687964 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3851851851851852, "acc_stderr": 0.029670906124630882, "acc_norm": 0.3851851851851852, "acc_norm
