open-llm-leaderboard-old/details_openthaigpt__openthaigpt-1.0.0-70b-chat
收藏数据集概述
数据集摘要
该数据集是在对模型 openthaigpt/openthaigpt-1.0.0-70b-chat 进行评估运行期间自动创建的，评估结果展示在 Open LLM Leaderboard 上。
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割找到，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_openthaigpt__openthaigpt-1.0.0-70b-chat", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-10T03:05:53.315743 运行的最新结果：
python { "all": { "acc": 0.6526209064314227, "acc_stderr": 0.031645785157839446, "acc_norm": 0.6584396509808794, "acc_norm_stderr": 0.03226896841560862, "mc1": 0.3623011015911873, "mc1_stderr": 0.016826646897262258, "mc2": 0.5423050166068909, "mc2_stderr": 0.015429015464878128 }, "harness|arc:challenge|25": { "acc": 0.6083617747440273, "acc_stderr": 0.014264122124938222, "acc_norm": 0.64419795221843, "acc_norm_stderr": 0.013990571137918765 }, "harness|hellaswag|10": { "acc": 0.661521609241187, "acc_stderr": 0.004722250355106678, "acc_norm": 0.8508265285799641, "acc_norm_stderr": 0.0035553128780523996 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.04171654161354543, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.04171654161354543 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998905, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998905 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6981132075471698, "acc_stderr": 0.028254200344438665, "acc_norm": 0.6981132075471698, "acc_norm_stderr": 0.028254200344438665 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.03476590104304135, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.03476590104304135 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5722543352601156, "acc_stderr": 0.03772446857518026, "acc_norm": 0.5722543352601156, "acc_norm_stderr": 0.03772446857518026 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287533, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287533 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6085106382978723, "acc_stderr": 0.03190701242326812, "acc_norm": 0.6085106382978723, "acc_norm_stderr": 0.03190701242326812 }, "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": 0.5241379310344828, "acc_stderr": 0.041618085035015295, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.041618085035015295 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42063492063492064, "acc_stderr": 0.025424835086923992, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.025424835086923992 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7709677419354839, "acc_stderr": 0.02390491431178265, "acc_norm": 0.7709677419354839, "acc_norm_stderr": 0.02390491431178265 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4729064039408867, "acc_stderr": 0.03512819077876106, "acc_norm": 0.4729064039408867, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8303030303030303, "acc_stderr": 0.02931118867498312, "acc_norm": 0.8303030303030303, "acc_norm_stderr": 0.02931118867498312 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8131313131313131, "acc_stderr": 0.027772533334218957, "acc_norm": 0.8131313131313131, "acc_norm_stderr": 0.027772533334218957 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.020986854593289698, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.020986854593289698 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6615384615384615, "acc_stderr": 0.023991500500313036, "acc_norm": 0.6615384615384615, "acc_norm_stderr": 0.023991500500313036 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.02773896
