open-llm-leaderboard-old/details_louisbrulenaudet__Maxine-34B-stock
收藏数据集概述
该数据集是在对模型 louisbrulenaudet/Maxine-34B-stock 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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。
- 数据集由 1 次运行创建，每次运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。
- "train" 拆分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_louisbrulenaudet__Maxine-34B-stock", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-05T00:59:27.637181 运行的最新结果：
python { "all": { "acc": 0.764333755853148, "acc_stderr": 0.028344527076434468, "acc_norm": 0.767478256941674, "acc_norm_stderr": 0.028893491881214303, "mc1": 0.5263157894736842, "mc1_stderr": 0.017479241161975457, "mc2": 0.7017750053458277, "mc2_stderr": 0.014211541851082555 }, "harness|arc:challenge|25": { "acc": 0.7192832764505119, "acc_stderr": 0.013131238126975583, "acc_norm": 0.7406143344709898, "acc_norm_stderr": 0.012808273573927094 }, "harness|hellaswag|10": { "acc": 0.671081457876917, "acc_stderr": 0.004688601416815173, "acc_norm": 0.8673571001792472, "acc_norm_stderr": 0.0033849518032134734 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7407407407407407, "acc_stderr": 0.03785714465066653, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.03785714465066653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.881578947368421, "acc_stderr": 0.02629399585547494, "acc_norm": 0.881578947368421, "acc_norm_stderr": 0.02629399585547494 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909284, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8075471698113208, "acc_stderr": 0.024262979839372274, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9097222222222222, "acc_stderr": 0.023964965777906935, "acc_norm": 0.9097222222222222, "acc_norm_stderr": 0.023964965777906935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.04960449637488584, "acc_norm": 0.58, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.45, "acc_stderr": 0.04999999999999999, "acc_norm": 0.45, "acc_norm_stderr": 0.04999999999999999 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7283236994219653, "acc_stderr": 0.0339175032232166, "acc_norm": 0.7283236994219653, "acc_norm_stderr": 0.0339175032232166 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5392156862745098, "acc_stderr": 0.04959859966384181, "acc_norm": 0.5392156862745098, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7702127659574468, "acc_stderr": 0.02750175294441242, "acc_norm": 0.7702127659574468, "acc_norm_stderr": 0.02750175294441242 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.04598188057816542, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.04598188057816542 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7586206896551724, "acc_stderr": 0.03565998174135302, "acc_norm": 0.7586206896551724, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7354497354497355, "acc_stderr": 0.022717467897708614, "acc_norm": 0.7354497354497355, "acc_norm_stderr": 0.022717467897708614 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5396825396825397, "acc_stderr": 0.04458029125470973, "acc_norm": 0.5396825396825397, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.62, "acc_stderr": 0.04878317312145632, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9064516129032258, "acc_stderr": 0.01656575466827098, "acc_norm": 0.9064516129032258, "acc_norm_stderr": 0.01656575466827098 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6748768472906403, "acc_stderr": 0.032957975663112704, "acc_norm": 0.6748768472906403, "acc_norm_stderr": 0.032957975663112704 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8666666666666667, "acc_stderr": 0.026544435312706467, "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.026544435312706467 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9242424242424242, "acc_stderr": 0.018852670234993093, "acc_norm": 0.9242424242424242, "acc_norm_stderr": 0.018852670234993093 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9740932642487047, "acc_stderr": 0.011464523356953162, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.011464523356953162 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8051282051282052, "acc_stderr": 0.020083167595181393, "acc_norm": 0.8051282051282052, "acc_norm_stderr": 0.020083167595181393 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.45555555555555555, "acc_stderr": 0.030364862504824428, "acc_norm": 0.45555555555555
