open-llm-leaderboard-old/details_h2oai__h2ogpt-research-oasst1-llama-65b
收藏数据集概述
数据集摘要
该数据集是在模型 h2oai/h2ogpt-research-oasst1-llama-65b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集包含 61 个配置，每个配置对应一个评估任务。
数据集结构
- 数据集由 61 个配置组成，每个配置对应一个评估任务。
- 数据集从 2 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_h2oai__h2ogpt-research-oasst1-llama-65b", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-08-17T22:10:29.981773 运行的最新结果：
python { "all": { "acc": 0.6359037673839993, "acc_stderr": 0.0329346816196445, "acc_norm": 0.6396809356138717, "acc_norm_stderr": 0.03290965482744071, "mc1": 0.34394124847001223, "mc1_stderr": 0.01662908751427678, "mc2": 0.48845185520886875, "mc2_stderr": 0.014057830912491135 }, "harness|arc:challenge|25": { "acc": 0.6177474402730375, "acc_stderr": 0.014200454049979275, "acc_norm": 0.6476109215017065, "acc_norm_stderr": 0.01396014260059868 }, "harness|hellaswag|10": { "acc": 0.6664011153156741, "acc_stderr": 0.004705347137699622, "acc_norm": 0.8593905596494722, "acc_norm_stderr": 0.0034690778470563765 }, "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": 0.562962962962963, "acc_stderr": 0.042849586397534015, "acc_norm": 0.562962962962963, "acc_norm_stderr": 0.042849586397534015 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.75, "acc_stderr": 0.03523807393012047, "acc_norm": 0.75, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6339622641509434, "acc_stderr": 0.029647813539365245, "acc_norm": 0.6339622641509434, "acc_norm_stderr": 0.029647813539365245 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7083333333333334, "acc_stderr": 0.03800968060554858, "acc_norm": 0.7083333333333334, "acc_norm_stderr": 0.03800968060554858 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5549132947976878, "acc_stderr": 0.03789401760283648, "acc_norm": 0.5549132947976878, "acc_norm_stderr": 0.03789401760283648 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201942, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201942 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6, "acc_stderr": 0.03202563076101737, "acc_norm": 0.6, "acc_norm_stderr": 0.03202563076101737 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.38596491228070173, "acc_stderr": 0.04579639422070434, "acc_norm": 0.38596491228070173, "acc_norm_stderr": 0.04579639422070434 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3783068783068783, "acc_stderr": 0.024976954053155254, "acc_norm": 0.3783068783068783, "acc_norm_stderr": 0.024976954053155254 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7483870967741936, "acc_stderr": 0.024685979286239963, "acc_norm": 0.7483870967741936, "acc_norm_stderr": 0.024685979286239963 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4039408866995074, "acc_stderr": 0.0345245390382204, "acc_norm": 0.4039408866995074, "acc_norm_stderr": 0.0345245390382204 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.047258156262526066, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526066 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8, "acc_stderr": 0.031234752377721164, "acc_norm": 0.8, "acc_norm_stderr": 0.031234752377721164 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.803030303030303, "acc_stderr": 0.028335609732463355, "acc_norm": 0.803030303030303, "acc_norm_stderr": 0.028335609732463355 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.023814477086593542, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.023814477086593542 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6256410256410256, "acc_stderr": 0.024537591572830513, "acc_norm": 0.6256410256410256, "acc_norm_stderr": 0.024537591572830513 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.02840653309060846, "acc_norm": 0.31851851851851853, "acc_norm_stderr": 0.02840653309060846 },
