open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-356m-instruct
收藏数据集概述
数据集简介
该数据集是在对模型AI-Sweden-Models/gpt-sw3-356m-instruct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。"train"分割始终指向最新的结果。
额外配置
一个额外的配置"results"存储了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_AI-Sweden-Models__gpt-sw3-356m-instruct", "harness_winogrande_5", split="train")
最新结果
以下是2023-12-06T17:41:35.635496运行的最新结果：
python { "all": { "acc": 0.2566151994762497, "acc_stderr": 0.030948731272392564, "acc_norm": 0.2576874821710207, "acc_norm_stderr": 0.03171291031197233, "mc1": 0.2484700122399021, "mc1_stderr": 0.015127427096520667, "mc2": 0.407425017285801, "mc2_stderr": 0.014703540024541484 }, "harness|arc:challenge|25": { "acc": 0.23037542662116042, "acc_stderr": 0.01230492841874761, "acc_norm": 0.2696245733788396, "acc_norm_stderr": 0.012968040686869157 }, "harness|hellaswag|10": { "acc": 0.326229834694284, "acc_stderr": 0.004678743563766644, "acc_norm": 0.3801035650268871, "acc_norm_stderr": 0.00484419991017304 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.1925925925925926, "acc_stderr": 0.03406542058502653, "acc_norm": 0.1925925925925926, "acc_norm_stderr": 0.03406542058502653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.15789473684210525, "acc_stderr": 0.029674167520101425, "acc_norm": 0.15789473684210525, "acc_norm_stderr": 0.029674167520101425 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2188679245283019, "acc_stderr": 0.025447863825108632, "acc_norm": 0.2188679245283019, "acc_norm_stderr": 0.025447863825108632 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.24855491329479767, "acc_stderr": 0.03295304696818318, "acc_norm": 0.24855491329479767, "acc_norm_stderr": 0.03295304696818318 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.28431372549019607, "acc_stderr": 0.04488482852329017, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.04488482852329017 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2765957446808511, "acc_stderr": 0.02924188386962883, "acc_norm": 0.2765957446808511, "acc_norm_stderr": 0.02924188386962883 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.03999423879281335, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.03999423879281335 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24603174603174602, "acc_stderr": 0.02218203720294836, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.02218203720294836 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.20634920634920634, "acc_stderr": 0.0361960452412425, "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.0361960452412425 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.1967741935483871, "acc_stderr": 0.022616409420742018, "acc_norm": 0.1967741935483871, "acc_norm_stderr": 0.022616409420742018 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.21182266009852216, "acc_stderr": 0.028748983689941072, "acc_norm": 0.21182266009852216, "acc_norm_stderr": 0.028748983689941072 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.23030303030303031, "acc_stderr": 0.03287666758603488, "acc_norm": 0.23030303030303031, "acc_norm_stderr": 0.03287666758603488 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.1919191919191919, "acc_stderr": 0.02805779167298901, "acc_norm": 0.1919191919191919, "acc_norm_stderr": 0.02805779167298901 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.34196891191709844, "acc_stderr": 0.03423465100104281, "acc_norm": 0.34196891191709844, "acc_norm_stderr": 0.03423465100104281 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3153846153846154, "acc_stderr": 0.02355964698318994, "acc_norm": 0.3153846153846154, "acc_norm_stderr": 0.02355964698318994 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.026202766534652148, "acc_norm": 0.244444
