open-llm-leaderboard-old/details_namirocks__tutor-model-13b-ep3
收藏数据集概述
数据集简介
该数据集是在对模型 namirocks/tutor-model-13b-ep3 进行评估运行期间自动创建的，用于 Open LLM Leaderboard 上的评估。
数据集组成
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集从1次运行中创建。每个运行在每个配置中作为一个特定的分割存在，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_namirocks__tutor-model-13b-ep3", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-23T14:22:10.523504 运行的最新结果：
python { "all": { "acc": 0.565791735957054, "acc_stderr": 0.03351962241327427, "acc_norm": 0.5744059102733704, "acc_norm_stderr": 0.03427708379273797, "mc1": 0.3537331701346389, "mc1_stderr": 0.016737814358846147, "mc2": 0.5298607855616481, "mc2_stderr": 0.015266264009722644 }, "harness|arc:challenge|25": { "acc": 0.5298634812286689, "acc_stderr": 0.014585305840007105, "acc_norm": 0.5733788395904437, "acc_norm_stderr": 0.014453185592920293 }, "harness|hellaswag|10": { "acc": 0.6179047998406691, "acc_stderr": 0.004849065962692133, "acc_norm": 0.8150766779525991, "acc_norm_stderr": 0.0038744190656586222 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45185185185185184, "acc_stderr": 0.04299268905480864, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.04299268905480864 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5789473684210527, "acc_stderr": 0.040179012759817494, "acc_norm": 0.5789473684210527, "acc_norm_stderr": 0.040179012759817494 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6075471698113207, "acc_stderr": 0.03005258057955785, "acc_norm": 0.6075471698113207, "acc_norm_stderr": 0.03005258057955785 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6527777777777778, "acc_stderr": 0.039812405437178615, "acc_norm": 0.6527777777777778, "acc_norm_stderr": 0.039812405437178615 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.05021167315686781, "acc_norm": 0.48, "acc_norm_stderr": 0.05021167315686781 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5260115606936416, "acc_stderr": 0.038073017265045125, "acc_norm": 0.5260115606936416, "acc_norm_stderr": 0.038073017265045125 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4297872340425532, "acc_stderr": 0.03236214467715564, "acc_norm": 0.4297872340425532, "acc_norm_stderr": 0.03236214467715564 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.040969851398436716, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.040969851398436716 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5172413793103449, "acc_stderr": 0.04164188720169375, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.04164188720169375 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3253968253968254, "acc_stderr": 0.024130158299762613, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.024130158299762613 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6774193548387096, "acc_stderr": 0.026593084516572274, "acc_norm": 0.6774193548387096, "acc_norm_stderr": 0.026593084516572274 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4827586206896552, "acc_stderr": 0.035158955511656986, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.58, "acc_stderr": 0.04960449637488584, "acc_norm": 0.58, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7090909090909091, "acc_stderr": 0.03546563019624336, "acc_norm": 0.7090909090909091, "acc_norm_stderr": 0.03546563019624336 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.696969696969697, "acc_stderr": 0.032742879140268674, "acc_norm": 0.696969696969697, "acc_norm_stderr": 0.032742879140268674 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8186528497409327, "acc_stderr": 0.027807032360686088, "acc_norm": 0.8186528497409327, "acc_norm_stderr": 0.027807032360686088 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5743589743589743, "acc_stderr": 0.02506909438729653, "acc_norm": 0.5743589743589743, "acc_norm_stderr": 0.02506909438729653 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.028406533090608463, "acc_norm": 0.31851851851851853, "acc_norm_
