open-llm-leaderboard-old/details_sumo43__Yi-34b-x2
收藏数据集概述
数据集来源
- 数据集是在评估模型 sumo43/Yi-34b-x2 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
- 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_sumo43__Yi-34b-x2", "harness_winogrande_5", split="train")
最新结果
- 这些是最新的结果，来自 2024-01-15T15:14:57.925776 的运行。
python { "all": { "acc": 0.7619039072175088, "acc_stderr": 0.028287211728702223, "acc_norm": 0.7672823242487893, "acc_norm_stderr": 0.028809880216771097, "mc1": 0.5740514075887393, "mc1_stderr": 0.01731047190407654, "mc2": 0.7210377690522727, "mc2_stderr": 0.014187472355015407 }, "harness|arc:challenge|25": { "acc": 0.6979522184300341, "acc_stderr": 0.013417519144716417, "acc_norm": 0.7286689419795221, "acc_norm_stderr": 0.012993807727545796 }, "harness|hellaswag|10": { "acc": 0.665803624775941, "acc_stderr": 0.004707447244200623, "acc_norm": 0.8570005974905397, "acc_norm_stderr": 0.0034935679140932928 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7481481481481481, "acc_stderr": 0.03749850709174021, "acc_norm": 0.7481481481481481, "acc_norm_stderr": 0.03749850709174021 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.868421052631579, "acc_stderr": 0.027508689533549912, "acc_norm": 0.868421052631579, "acc_norm_stderr": 0.027508689533549912 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8075471698113208, "acc_stderr": 0.024262979839372274, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8888888888888888, "acc_stderr": 0.026280550932848052, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.026280550932848052 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "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": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "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": 0.5784313725490197, "acc_stderr": 0.04913595201274503, "acc_norm": 0.5784313725490197, "acc_norm_stderr": 0.04913595201274503 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7702127659574468, "acc_stderr": 0.027501752944412417, "acc_norm": 0.7702127659574468, "acc_norm_stderr": 0.027501752944412417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5964912280701754, "acc_stderr": 0.04615186962583707, "acc_norm": 0.5964912280701754, "acc_norm_stderr": 0.04615186962583707 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7241379310344828, "acc_stderr": 0.037245636197746304, "acc_norm": 0.7241379310344828, "acc_norm_stderr": 0.037245636197746304 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7116402116402116, "acc_stderr": 0.023330654054535903, "acc_norm": 0.7116402116402116, "acc_norm_stderr": 0.023330654054535903 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6111111111111112, "acc_stderr": 0.04360314860077459, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9096774193548387, "acc_stderr": 0.016306570644488313, "acc_norm": 0.9096774193548387, "acc_norm_stderr": 0.016306570644488313 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.645320197044335, "acc_stderr": 0.03366124489051449, "acc_norm": 0.645320197044335, "acc_norm_stderr": 0.03366124489051449 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.82, "acc_stderr": 0.03861229196653694, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8666666666666667, "acc_stderr": 0.026544435312706456, "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.026544435312706456 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9191919191919192, "acc_stderr": 0.019417681889724536, "acc_norm": 0.9191919191919192, "acc_norm_stderr": 0.019417681889724536 }, "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": 0.8153846153846154, "acc_stderr": 0.01967163241310029, "acc_norm": 0.8153846153846154, "acc_norm_stderr": 0.01967163241310029 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.45185185185185184, "acc_stderr": 0.030343862998512623, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.030343862998512623 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.82
