open-llm-leaderboard-old/details_chlee10__T3Q-platypus-SOLAR-10.7B-v1.0
收藏数据集概述
数据集名称
- 名称: Evaluation run of chlee10/T3Q-platypus-SOLAR-10.7B-v1.0
数据集描述
- 创建目的: 该数据集是在评估模型 chlee10/T3Q-platypus-SOLAR-10.7B-v1.0 在 Open LLM Leaderboard 上的运行过程中自动创建的。
- 组成: 数据集包含 63 个配置，每个配置对应一个评估任务。
- 创建次数: 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。
- 额外配置: 一个名为 "results" 的额外配置存储了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_chlee10__T3Q-platypus-SOLAR-10.7B-v1.0", "harness_winogrande_5", split="train")
最新结果
- 最新结果: 这些是最新结果，来自 2024-03-12T05:44:28.893890 的运行。
python { "all": { "acc": 0.6161023263287835, "acc_stderr": 0.03279616909498795, "acc_norm": 0.6233676222297954, "acc_norm_stderr": 0.03351736415113747, "mc1": 0.3525091799265606, "mc1_stderr": 0.016724646380756547, "mc2": 0.5191281080553253, "mc2_stderr": 0.014792664772089011 }, "harness|arc:challenge|25": { "acc": 0.5887372013651877, "acc_stderr": 0.014379441068522082, "acc_norm": 0.6254266211604096, "acc_norm_stderr": 0.014144193471893447 }, "harness|hellaswag|10": { "acc": 0.6443935471021709, "acc_stderr": 0.004777183508949811, "acc_norm": 0.8414658434574785, "acc_norm_stderr": 0.003644946730044617 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6842105263157895, "acc_stderr": 0.0378272898086547, "acc_norm": 0.6842105263157895, "acc_norm_stderr": 0.0378272898086547 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6641509433962264, "acc_stderr": 0.02906722014664483, "acc_norm": 0.6641509433962264, "acc_norm_stderr": 0.02906722014664483 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7152777777777778, "acc_stderr": 0.03773809990686934, "acc_norm": 0.7152777777777778, "acc_norm_stderr": 0.03773809990686934 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6011560693641619, "acc_stderr": 0.0373362665538351, "acc_norm": 0.6011560693641619, "acc_norm_stderr": 0.0373362665538351 }, "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": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5276595744680851, "acc_stderr": 0.03263597118409769, "acc_norm": 0.5276595744680851, "acc_norm_stderr": 0.03263597118409769 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.42105263157894735, "acc_stderr": 0.046446020912223177, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.041227371113703316, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.041227371113703316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.43386243386243384, "acc_stderr": 0.0255250343824749, "acc_norm": 0.43386243386243384, "acc_norm_stderr": 0.0255250343824749 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04360314860077459, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7161290322580646, "acc_stderr": 0.025649381063029258, "acc_norm": 0.7161290322580646, "acc_norm_stderr": 0.025649381063029258 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4876847290640394, "acc_stderr": 0.035169204442208966, "acc_norm": 0.4876847290640394, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621504, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.02985751567338642, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.02985751567338642 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8911917098445595, "acc_stderr": 0.022473253332768763, "acc_norm": 0.8911917098445595, "acc_norm_stderr": 0.022473253332768763 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6051282051282051, "acc_stderr": 0.02478431694215639, "acc_norm": 0.6051282051282051, "acc_norm_stderr": 0.02478431694215639 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35555555555555557, "acc_stderr": 0.029185714949857406, "acc_norm": 0.355
