open-llm-leaderboard-old/details_ALBADDAWI__DeepCode-7B-Aurora-v12
收藏数据集概述
数据集来源
该数据集是在评估模型 ALBADDAWI/DeepCode-7B-Aurora-v12 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。数据集是从 1 次运行中创建的，每次运行的详细信息可以在每个配置中找到，以运行的时间戳命名的特定分片形式存储。"train" 分片始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
数据加载示例
以下是加载特定运行详细信息的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ALBADDAWI__DeepCode-7B-Aurora-v12", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-15T12:09:06.672545 运行 的最新结果： python { "all": { "acc": 0.5608472572462677, "acc_stderr": 0.03441135950327688, "acc_norm": 0.570942735618394, "acc_norm_stderr": 0.03523740581436983, "mc1": 0.2962056303549572, "mc1_stderr": 0.015983595101811392, "mc2": 0.4045536284239386, "mc2_stderr": 0.015301568217358057 }, "harness|arc:challenge|25": { "acc": 0.5264505119453925, "acc_stderr": 0.014590931358120169, "acc_norm": 0.5554607508532423, "acc_norm_stderr": 0.014521226405627084 }, "harness|hellaswag|10": { "acc": 0.5486954789882493, "acc_stderr": 0.004966060995315059, "acc_norm": 0.7237602071300537, "acc_norm_stderr": 0.004462230363982152 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411022, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411022 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4, "acc_stderr": 0.04232073695151589, "acc_norm": 0.4, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.03910525752849724, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.03910525752849724 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5547169811320755, "acc_stderr": 0.030588052974270655, "acc_norm": 0.5547169811320755, "acc_norm_stderr": 0.030588052974270655 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325582, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325582 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.05021167315686779, "acc_norm": 0.52, "acc_norm_stderr": 0.05021167315686779 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.05021167315686779, "acc_norm": 0.48, "acc_norm_stderr": 0.05021167315686779 }, "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": 0.5549132947976878, "acc_stderr": 0.03789401760283647, "acc_norm": 0.5549132947976878, "acc_norm_stderr": 0.03789401760283647 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.046882617226215055, "acc_norm": 0.68, "acc_norm_stderr": 0.046882617226215055 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6425531914893617, "acc_stderr": 0.031329417894764254, "acc_norm": 0.6425531914893617, "acc_norm_stderr": 0.031329417894764254 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6275862068965518, "acc_stderr": 0.0402873153294756, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.0402873153294756 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.582010582010582, "acc_stderr": 0.02540255550326091, "acc_norm": 0.582010582010582, "acc_norm_stderr": 0.02540255550326091 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6258064516129033, "acc_stderr": 0.027528904299845704, "acc_norm": 0.6258064516129033, "acc_norm_stderr": 0.027528904299845704 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5270935960591133, "acc_stderr": 0.03512819077876105, "acc_norm": 0.5270935960591133, "acc_norm_stderr": 0.03512819077876105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.703030303030303, "acc_stderr": 0.035679697722680495, "acc_norm": 0.703030303030303, "acc_norm_stderr": 0.035679697722680495 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.702020202020202, "acc_stderr": 0.03258630383836556, "acc_norm": 0.702020202020202, "acc_norm_stderr": 0.03258630383836556 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6735751295336787, "acc_stderr": 0.033840286211432945, "acc_norm": 0.6735751295336787, "acc_norm_stderr": 0.033840286211432945 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5692307692307692, "acc_stderr": 0.025106820660539753, "acc_norm": 0.5692307692307692, "acc_norm_stderr": 0.025106820660539753 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4185185185185185, "acc_stderr": 0.030078013075022055, "acc_norm": 0.4185185185185185, "acc_norm_stderr": 0.0
