open-llm-leaderboard-old/details_kalisai__Nusantara-2.7b-Indo-Chat
收藏数据集概述
数据集摘要
该数据集是在评估模型 kalisai/Nusantara-2.7b-Indo-Chat 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
- 该数据集包含 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。
- 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_kalisai__Nusantara-2.7b-Indo-Chat", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-11T04:47:23.524103 运行的最新结果：
python { "all": { "acc": 0.2542728532923772, "acc_stderr": 0.030711833159814798, "acc_norm": 0.2551649256395204, "acc_norm_stderr": 0.031440012883894586, "mc1": 0.23990208078335373, "mc1_stderr": 0.014948812679062133, "mc2": 0.3740723994774855, "mc2_stderr": 0.014147606839280165 }, "harness|arc:challenge|25": { "acc": 0.310580204778157, "acc_stderr": 0.013522292098053054, "acc_norm": 0.34215017064846415, "acc_norm_stderr": 0.013864152159177282 }, "harness|hellaswag|10": { "acc": 0.4334793865763792, "acc_stderr": 0.004945424771611596, "acc_norm": 0.5610436168094005, "acc_norm_stderr": 0.004952454721934799 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.25925925925925924, "acc_stderr": 0.03785714465066654, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.03785714465066654 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.20754716981132076, "acc_stderr": 0.02495991802891127, "acc_norm": 0.20754716981132076, "acc_norm_stderr": 0.02495991802891127 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "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": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23699421965317918, "acc_stderr": 0.03242414757483098, "acc_norm": 0.23699421965317918, "acc_norm_stderr": 0.03242414757483098 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617746, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617746 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.22758620689655173, "acc_stderr": 0.03493950380131184, "acc_norm": 0.22758620689655173, "acc_norm_stderr": 0.03493950380131184 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24867724867724866, "acc_stderr": 0.022261817692400168, "acc_norm": 0.24867724867724866, "acc_norm_stderr": 0.022261817692400168 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.039325376803928724, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.039325376803928724 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.20967741935483872, "acc_stderr": 0.02315787934908352, "acc_norm": 0.20967741935483872, "acc_norm_stderr": 0.02315787934908352 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.18226600985221675, "acc_stderr": 0.02716334085964515, "acc_norm": 0.18226600985221675, "acc_norm_stderr": 0.02716334085964515 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2727272727272727, "acc_stderr": 0.03477691162163659, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.03477691162163659 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2878787878787879, "acc_stderr": 0.03225883512300992, "acc_norm": 0.2878787878787879, "acc_norm_stderr": 0.03225883512300992 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.20725388601036268, "acc_stderr": 0.02925282329180361, "acc_norm": 0.20725388601036268, "acc_norm_stderr": 0.02925282329180361 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2076923076923077, "acc_stderr": 0.0205675395672468, "acc_norm": 0.2076923076923077, "acc_norm_stderr": 0.0205675395672468 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.22592592592592592, "acc_stderr": 0.02549753263960955
