open-llm-leaderboard-old/details_jondurbin__bagel-dpo-34b-v0.5
收藏数据集概述
数据集摘要
该数据集是在评估模型jondurbin/bagel-dpo-34b-v0.5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作为一个特定的分片找到，分片名称使用运行的时间戳。
- "train"分片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_jondurbin__bagel-dpo-34b-v0.5", "harness_winogrande_5", split="train")
最新结果
这些是最新结果，来自2024-04-03T06:54:38.320511的运行： python { "all": { "acc": 0.7525591398123552, "acc_stderr": 0.02863817242928347, "acc_norm": 0.7579003255896788, "acc_norm_stderr": 0.02917451311850848, "mc1": 0.4810281517747858, "mc1_stderr": 0.01749089640576235, "mc2": 0.6507941130904138, "mc2_stderr": 0.015048541170172984 }, "harness|arc:challenge|25": { "acc": 0.6604095563139932, "acc_stderr": 0.01383903976282017, "acc_norm": 0.6834470989761092, "acc_norm_stderr": 0.01359243151906808 }, "harness|hellaswag|10": { "acc": 0.6439952200756821, "acc_stderr": 0.004778380758851131, "acc_norm": 0.8379804819757021, "acc_norm_stderr": 0.003677156687848828 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7185185185185186, "acc_stderr": 0.038850042458002526, "acc_norm": 0.7185185185185186, "acc_norm_stderr": 0.038850042458002526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.881578947368421, "acc_stderr": 0.026293995855474938, "acc_norm": 0.881578947368421, "acc_norm_stderr": 0.026293995855474938 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8226415094339623, "acc_stderr": 0.023508739218846938, "acc_norm": 0.8226415094339623, "acc_norm_stderr": 0.023508739218846938 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8819444444444444, "acc_stderr": 0.026983346503309358, "acc_norm": 0.8819444444444444, "acc_norm_stderr": 0.026983346503309358 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "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": 0.6878612716763006, "acc_stderr": 0.035331333893236574, "acc_norm": 0.6878612716763006, "acc_norm_stderr": 0.035331333893236574 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5980392156862745, "acc_stderr": 0.048786087144669955, "acc_norm": 0.5980392156862745, "acc_norm_stderr": 0.048786087144669955 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.03942772444036624, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7829787234042553, "acc_stderr": 0.026947483121496234, "acc_norm": 0.7829787234042553, "acc_norm_stderr": 0.026947483121496234 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.045981880578165414, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7655172413793103, "acc_stderr": 0.035306258743465914, "acc_norm": 0.7655172413793103, "acc_norm_stderr": 0.035306258743465914 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7142857142857143, "acc_stderr": 0.023266512213730557, "acc_norm": 0.7142857142857143, "acc_norm_stderr": 0.023266512213730557 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5238095238095238, "acc_stderr": 0.04467062628403273, "acc_norm": 0.5238095238095238, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8903225806451613, "acc_stderr": 0.017776778700485184, "acc_norm": 0.8903225806451613, "acc_norm_stderr": 0.017776778700485184 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6009852216748769, "acc_stderr": 0.03445487686264716, "acc_norm": 0.6009852216748769, "acc_norm_stderr": 0.03445487686264716 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.81, "acc_stderr": 0.03942772444036624, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8909090909090909, "acc_stderr": 0.02434383813514564, "acc_norm": 0.8909090909090909, "acc_norm_stderr": 0.02434383813514564 }, "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": 0.9637305699481865, "acc_stderr": 0.013492659751295134, "acc_norm": 0.9637305699481865, "acc_norm_stderr": 0.013492659751295134 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7794871794871795, "acc_stderr": 0.02102067268082791, "acc_norm": 0.7794871794871795, "acc_norm_stderr": 0.02102067268082791 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4444444444444444, "acc_stderr": 0.030296771286067323, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.030296771286067323 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.84
