open-llm-leaderboard-old/details_AA051612__B0122
收藏数据集概述
该数据集是在模型 AA051612/B0122 的评估运行期间自动创建的，用于 Open LLM Leaderboard。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
- 创建来源：数据集从 1 次运行中创建，每次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。
- 分割：每个配置包含多个分割，其中 "train" 分割始终指向最新的结果。
- 结果配置：一个额外的 "results" 配置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_AA051612__B0122", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-22T18:14:13.351822 运行的最新结果：
python { "all": { "acc": 0.8018093992937142, "acc_stderr": 0.025943636891982935, "acc_norm": 0.8135255711326126, "acc_norm_stderr": 0.026390358482713747, "mc1": 0.401468788249694, "mc1_stderr": 0.017160273901693654, "mc2": 0.581997849772674, "mc2_stderr": 0.01539700975904714 }, "harness|arc:challenge|25": { "acc": 0.643344709897611, "acc_stderr": 0.013998056902620194, "acc_norm": 0.6791808873720137, "acc_norm_stderr": 0.01364094309194653 }, "harness|hellaswag|10": { "acc": 0.6594303923521211, "acc_stderr": 0.004729322613301549, "acc_norm": 0.8492332204740092, "acc_norm_stderr": 0.0035709011883580744 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.8222222222222222, "acc_stderr": 0.03302789859901717, "acc_norm": 0.8222222222222222, "acc_norm_stderr": 0.03302789859901717 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.868421052631579, "acc_stderr": 0.027508689533549912, "acc_norm": 0.868421052631579, "acc_norm_stderr": 0.027508689533549912 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.81, "acc_stderr": 0.03942772444036623, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8679245283018868, "acc_stderr": 0.020837715430694004, "acc_norm": 0.8679245283018868, "acc_norm_stderr": 0.020837715430694004 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9305555555555556, "acc_stderr": 0.021257974822832048, "acc_norm": 0.9305555555555556, "acc_norm_stderr": 0.021257974822832048 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.71, "acc_stderr": 0.04560480215720684, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7745664739884393, "acc_stderr": 0.03186209851641144, "acc_norm": 0.7745664739884393, "acc_norm_stderr": 0.03186209851641144 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.6568627450980392, "acc_stderr": 0.04724007352383888, "acc_norm": 0.6568627450980392, "acc_norm_stderr": 0.04724007352383888 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8212765957446808, "acc_stderr": 0.025045373272050978, "acc_norm": 0.8212765957446808, "acc_norm_stderr": 0.025045373272050978 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6491228070175439, "acc_stderr": 0.04489539350270698, "acc_norm": 0.6491228070175439, "acc_norm_stderr": 0.04489539350270698 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8068965517241379, "acc_stderr": 0.03289445522127403, "acc_norm": 0.8068965517241379, "acc_norm_stderr": 0.03289445522127403 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7645502645502645, "acc_stderr": 0.021851509822031722, "acc_norm": 0.7645502645502645, "acc_norm_stderr": 0.021851509822031722 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5793650793650794, "acc_stderr": 0.04415438226743745, "acc_norm": 0.5793650793650794, "acc_norm_stderr": 0.04415438226743745 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.62, "acc_stderr": 0.048783173121456316, "acc_norm": 0.62, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9193548387096774, "acc_stderr": 0.015490002961591035, "acc_norm": 0.9193548387096774, "acc_norm_stderr": 0.015490002961591035 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6945812807881774, "acc_stderr": 0.03240661565868408, "acc_norm": 0.6945812807881774, "acc_norm_stderr": 0.03240661565868408 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.85, "acc_stderr": 0.035887028128263714, "acc_norm": 0.85, "acc_norm_stderr": 0.035887028128263714 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.9212121212121213, "acc_stderr": 0.021037183825716364, "acc_norm": 0.9212121212121213, "acc_norm_stderr": 0.021037183825716364 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9444444444444444, "acc_stderr": 0.0163199507007674, "acc_norm": 0.9444444444444444, "acc_norm_stderr": 0.0163199507007674 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9740932642487047, "acc_stderr": 0.01146452335695318, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.01146452335695318 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8717948717948718, "acc_stderr": 0.016950599120913946, "acc_norm": 0.8717948717948718, "acc_norm_stderr": 0.016950599120913946 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.5481481481481482, "acc_stderr": 0.030343862998512633, "acc_norm": 0.5481481481481482, "
