open-llm-leaderboard-old/details_OpenBuddy__openbuddy-qwen1.5-32b-v21.1-32k
收藏数据集概述
数据集简介
该数据集是在评估模型 OpenBuddy/openbuddy-qwen1.5-32b-v21.1-32k 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集来自1次运行。每个运行在每个配置中都有一个特定的分割，分割名称使用运行的时间戳。
- 训练分割："train" 分割始终指向最新的结果。
- 结果配置：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_OpenBuddy__openbuddy-qwen1.5-32b-v21.1-32k", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-10T12:35:48.776188 运行 的最新结果：
python { "all": { "acc": 0.733463931953177, "acc_stderr": 0.02957035174437335, "acc_norm": 0.7377650095701614, "acc_norm_stderr": 0.030137285715320282, "mc1": 0.38922888616891066, "mc1_stderr": 0.01706855268069033, "mc2": 0.5611514687959592, "mc2_stderr": 0.014919988896199053 }, "harness|arc:challenge|25": { "acc": 0.6040955631399317, "acc_stderr": 0.01429122839353659, "acc_norm": 0.6535836177474402, "acc_norm_stderr": 0.01390501118006323 }, "harness|hellaswag|10": { "acc": 0.6334395538737303, "acc_stderr": 0.0048088021145928465, "acc_norm": 0.8316072495518821, "acc_norm_stderr": 0.0037344989792073065 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720385, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.868421052631579, "acc_stderr": 0.027508689533549915, "acc_norm": 0.868421052631579, "acc_norm_stderr": 0.027508689533549915 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.78, "acc_stderr": 0.04163331998932262, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932262 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7547169811320755, "acc_stderr": 0.026480357179895685, "acc_norm": 0.7547169811320755, "acc_norm_stderr": 0.026480357179895685 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8611111111111112, "acc_stderr": 0.028919802956134905, "acc_norm": 0.8611111111111112, "acc_norm_stderr": 0.028919802956134905 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7109826589595376, "acc_stderr": 0.03456425745086998, "acc_norm": 0.7109826589595376, "acc_norm_stderr": 0.03456425745086998 }, "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": 0.82, "acc_stderr": 0.038612291966536934, "acc_norm": 0.82, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7617021276595745, "acc_stderr": 0.027851252973889778, "acc_norm": 0.7617021276595745, "acc_norm_stderr": 0.027851252973889778 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.046570472605949646, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.046570472605949646 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.696551724137931, "acc_stderr": 0.038312260488503336, "acc_norm": 0.696551724137931, "acc_norm_stderr": 0.038312260488503336 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6481481481481481, "acc_stderr": 0.024594975128920938, "acc_norm": 0.6481481481481481, "acc_norm_stderr": 0.024594975128920938 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5714285714285714, "acc_stderr": 0.04426266681379909, "acc_norm": 0.5714285714285714, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8709677419354839, "acc_stderr": 0.019070889254792753, "acc_norm": 0.8709677419354839, "acc_norm_stderr": 0.019070889254792753 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6600985221674877, "acc_stderr": 0.033327690684107895, "acc_norm": 0.6600985221674877, "acc_norm_stderr": 0.033327690684107895 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.84, "acc_stderr": 0.03684529491774709, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.027045948825865387, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865387 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9040404040404041, "acc_stderr": 0.020984808610047943, "acc_norm": 0.9040404040404041, "acc_norm_stderr": 0.020984808610047943 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9585492227979274, "acc_stderr": 0.014385432857476439, "acc_norm": 0.9585492227979274, "acc_norm_stderr": 0.014385432857476439 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.782051282051282, "acc_stderr": 0.02093244577446317, "acc_norm": 0.782051282051282, "acc_norm_stderr": 0.02093244577446317 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.448148148
