open-llm-leaderboard-old/details_BEE-spoke-data__Mixtral-GQA-400m-v2
收藏数据集概述
数据集简介
该数据集是在模型 BEE-spoke-data/Mixtral-GQA-400m-v2 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
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。
- 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_BEE-spoke-data__Mixtral-GQA-400m-v2", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-23T18:12:16.481327 运行的最新结果：
python { "all": { "acc": 0.25928519994733173, "acc_stderr": 0.03084201892972556, "acc_norm": 0.26026390145872735, "acc_norm_stderr": 0.03164977363535095, "mc1": 0.25458996328029376, "mc1_stderr": 0.015250117079156494, "mc2": 0.465481151431113, "mc2_stderr": 0.015410819143540583 }, "harness|arc:challenge|25": { "acc": 0.17064846416382254, "acc_stderr": 0.010993654168413738, "acc_norm": 0.2022184300341297, "acc_norm_stderr": 0.011737454431872104 }, "harness|hellaswag|10": { "acc": 0.2698665604461263, "acc_stderr": 0.004429831152914678, "acc_norm": 0.2778331009759012, "acc_norm_stderr": 0.004470152081675125 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.23703703703703705, "acc_stderr": 0.03673731683969506, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.03673731683969506 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.20394736842105263, "acc_stderr": 0.03279000406310053, "acc_norm": 0.20394736842105263, "acc_norm_stderr": 0.03279000406310053 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21509433962264152, "acc_stderr": 0.025288394502891363, "acc_norm": 0.21509433962264152, "acc_norm_stderr": 0.025288394502891363 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847415, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847415 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2023121387283237, "acc_stderr": 0.030631145539198813, "acc_norm": 0.2023121387283237, "acc_norm_stderr": 0.030631145539198813 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2765957446808511, "acc_stderr": 0.029241883869628806, "acc_norm": 0.2765957446808511, "acc_norm_stderr": 0.029241883869628806 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748141, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748141 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2206896551724138, "acc_stderr": 0.03455930201924811, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.03455930201924811 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.19047619047619047, "acc_stderr": 0.03512207412302052, "acc_norm": 0.19047619047619047, "acc_norm_stderr": 0.03512207412302052 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.2, "acc_stderr": 0.04020151261036847, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036847 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.02645087448904277, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.02645087448904277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2857142857142857, "acc_stderr": 0.0317852971064275, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0317852971064275 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.21, "acc_stderr": 0.04093601807403325, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403325 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2727272727272727, "acc_stderr": 0.03477691162163659, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.03477691162163659 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3282828282828283, "acc_stderr": 0.03345678422756777, "acc_norm": 0.3282828282828283, "acc_norm_stderr": 0.03345678422756777 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.27979274611398963, "acc_stderr": 0.03239637046735703, "acc_norm": 0.27979274611398963, "acc_norm_stderr": 0.03239637046735703 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3, "acc_stderr": 0.023234581088428494, "acc_norm": 0.3, "acc_norm_stderr": 0.023234581088428494 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.026842057873833706, "acc_norm": 0.2629629629629629
