open-llm-leaderboard-old/details_bhavinjawade__SOLAR-10B-Nector-DPO-Jawade
收藏数据集概述
该数据集是在评估模型 bhavinjawade/SOLAR-10B-Nector-DPO-Jawade 在 Open LLM Leaderboard 上的自动创建的。
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。
- 额外的配置 “results” 存储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
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_bhavinjawade__SOLAR-10B-Nector-DPO-Jawade", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-14T21:40:44.530689 运行的最新结果：
python { "all": { "acc": 0.6659513885128865, "acc_stderr": 0.03153636640803569, "acc_norm": 0.6668604037396749, "acc_norm_stderr": 0.03217609086906697, "mc1": 0.5618115055079559, "mc1_stderr": 0.01736923616440442, "mc2": 0.7092186670643685, "mc2_stderr": 0.01520446597729704 }, "harness|arc:challenge|25": { "acc": 0.6851535836177475, "acc_stderr": 0.01357265770308495, "acc_norm": 0.7133105802047781, "acc_norm_stderr": 0.013214986329274779 }, "harness|hellaswag|10": { "acc": 0.7124078868751245, "acc_stderr": 0.0045171484341804905, "acc_norm": 0.8861780521808404, "acc_norm_stderr": 0.0031694581233577238 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.041716541613545426, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.041716541613545426 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.75, "acc_stderr": 0.03523807393012047, "acc_norm": 0.75, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.04461960433384741, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6943396226415094, "acc_stderr": 0.028353298073322666, "acc_norm": 0.6943396226415094, "acc_norm_stderr": 0.028353298073322666 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8055555555555556, "acc_stderr": 0.03309615177059006, "acc_norm": 0.8055555555555556, "acc_norm_stderr": 0.03309615177059006 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.03643037168958548, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.03643037168958548 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6042553191489362, "acc_stderr": 0.031967586978353627, "acc_norm": 0.6042553191489362, "acc_norm_stderr": 0.031967586978353627 }, "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": 0.6137931034482759, "acc_stderr": 0.04057324734419036, "acc_norm": 0.6137931034482759, "acc_norm_stderr": 0.04057324734419036 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47619047619047616, "acc_stderr": 0.025722097064388535, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.025722097064388535 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.40476190476190477, "acc_stderr": 0.04390259265377562, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.04390259265377562 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8193548387096774, "acc_stderr": 0.021886178567172534, "acc_norm": 0.8193548387096774, "acc_norm_stderr": 0.021886178567172534 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.03517603540361008, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.03517603540361008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.03192271569548301, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.03192271569548301 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8838383838383839, "acc_stderr": 0.022828881775249377, "acc_norm": 0.8838383838383839, "acc_norm_stderr": 0.022828881775249377 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9119170984455959, "acc_stderr": 0.02045374660160103, "acc_norm": 0.9119170984455959, "acc_norm_stderr": 0.02045374660160103 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6717948717948717, "acc_stderr": 0.023807633198657262, "acc_norm": 0.6717948717948717, "acc_norm_stderr": 0.023807633198657262 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3814814814814815, "acc_stderr": 0.029616718927497593, "acc_norm": 0.3814814814814815, "acc_norm_stderr": 0.029616718927
