open-llm-leaderboard/details_ZhangShenao__0.001_idpo_declr_4iters_iter_3
收藏数据集概述
数据集简介
该数据集是在评估模型 ZhangShenao/0.001_idpo_declr_4iters_iter_3 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 数据来源：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。
- 最新结果："train" 分割始终指向最新的结果。
- 聚合结果：额外的 "results" 配置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_ZhangShenao__0.001_idpo_declr_4iters_iter_3", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-08T08:47:34.953273 运行的最新结果：
python { "all": { "acc": 0.6050759758521479, "acc_stderr": 0.03311893846776277, "acc_norm": 0.6114459885903942, "acc_norm_stderr": 0.03380911687393187, "mc1": 0.3488372093023256, "mc1_stderr": 0.016684419859986886, "mc2": 0.5033400649330749, "mc2_stderr": 0.01588434641111232 }, "harness|arc:challenge|25": { "acc": 0.5981228668941979, "acc_stderr": 0.014327268614578276, "acc_norm": 0.6305460750853242, "acc_norm_stderr": 0.014104578366491885 }, "harness|hellaswag|10": { "acc": 0.6579366660027883, "acc_stderr": 0.004734311435009194, "acc_norm": 0.8498307110137423, "acc_norm_stderr": 0.0035650718701954478 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5703703703703704, "acc_stderr": 0.042763494943765995, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.042763494943765995 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.631578947368421, "acc_stderr": 0.03925523381052932, "acc_norm": 0.631578947368421, "acc_norm_stderr": 0.03925523381052932 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6754716981132075, "acc_stderr": 0.02881561571343211, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.02881561571343211 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.03745554791462456, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.03745554791462456 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5838150289017341, "acc_stderr": 0.03758517775404947, "acc_norm": 0.5838150289017341, "acc_norm_stderr": 0.03758517775404947 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4803921568627451, "acc_stderr": 0.04971358884367405, "acc_norm": 0.4803921568627451, "acc_norm_stderr": 0.04971358884367405 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.044084400227680794, "acc_norm": 0.74, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5234042553191489, "acc_stderr": 0.03265019475033582, "acc_norm": 0.5234042553191489, "acc_norm_stderr": 0.03265019475033582 }, "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": 0.503448275862069, "acc_stderr": 0.04166567577101579, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.04166567577101579 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42328042328042326, "acc_stderr": 0.025446365634406772, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.025446365634406772 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.35714285714285715, "acc_stderr": 0.04285714285714281, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.04285714285714281 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7322580645161291, "acc_stderr": 0.025189006660212385, "acc_norm": 0.7322580645161291, "acc_norm_stderr": 0.025189006660212385 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7272727272727273, "acc_stderr": 0.0347769116216366, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.0347769116216366 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.029857515673386417, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.029857515673386417 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8290155440414507, "acc_stderr": 0.02717121368316453, "acc_norm": 0.8290155440414507, "acc_norm_stderr": 0.02717121368316453 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5666666666666667, "acc_stderr": 0.025124653525885113, "acc_norm": 0.5666666666666667, "acc_norm_stderr": 0.025124653525885113 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027
