open-llm-leaderboard-old/details_jondurbin__airoboros-34b-3.3
收藏数据集概述
数据集摘要
该数据集是在评估模型 jondurbin/airoboros-34b-3.3 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63
- 数据来源：1 次运行
- 数据分割：每个配置包含特定运行的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置："results" 配置存储所有运行的聚合结果，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_jondurbin__airoboros-34b-3.3", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-03T06:36:09.032058 运行的最新结果：
python { "all": { "acc": 0.7384979768935336, "acc_stderr": 0.028846149322558155, "acc_norm": 0.7486960506623671, "acc_norm_stderr": 0.02940148738177012, "mc1": 0.42472460220318237, "mc1_stderr": 0.017304000957167477, "mc2": 0.5958885847450273, "mc2_stderr": 0.015660972854187622 }, "harness|arc:challenge|25": { "acc": 0.6313993174061433, "acc_stderr": 0.014097810678042198, "acc_norm": 0.674061433447099, "acc_norm_stderr": 0.013697432466693247 }, "harness|hellaswag|10": { "acc": 0.6443935471021709, "acc_stderr": 0.0047771835089498085, "acc_norm": 0.8444532961561442, "acc_norm_stderr": 0.0036168436913607657 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7185185185185186, "acc_stderr": 0.03885004245800253, "acc_norm": 0.7185185185185186, "acc_norm_stderr": 0.03885004245800253 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.875, "acc_stderr": 0.026913523521537846, "acc_norm": 0.875, "acc_norm_stderr": 0.026913523521537846 }, "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": 0.8188679245283019, "acc_stderr": 0.023702963526757787, "acc_norm": 0.8188679245283019, "acc_norm_stderr": 0.023702963526757787 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.875, "acc_stderr": 0.02765610492929436, "acc_norm": 0.875, "acc_norm_stderr": 0.02765610492929436 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.63, "acc_stderr": 0.048523658709391, "acc_norm": 0.63, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6936416184971098, "acc_stderr": 0.03514942551267437, "acc_norm": 0.6936416184971098, "acc_norm_stderr": 0.03514942551267437 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5, "acc_stderr": 0.04975185951049946, "acc_norm": 0.5, "acc_norm_stderr": 0.04975185951049946 }, "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": 0.774468085106383, "acc_stderr": 0.027321078417387536, "acc_norm": 0.774468085106383, "acc_norm_stderr": 0.027321078417387536 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.04657047260594964, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.04657047260594964 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7310344827586207, "acc_stderr": 0.036951833116502325, "acc_norm": 0.7310344827586207, "acc_norm_stderr": 0.036951833116502325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6772486772486772, "acc_stderr": 0.024078943243597016, "acc_norm": 0.6772486772486772, "acc_norm_stderr": 0.024078943243597016 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9, "acc_stderr": 0.017066403719657258, "acc_norm": 0.9, "acc_norm_stderr": 0.017066403719657258 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.645320197044335, "acc_stderr": 0.0336612448905145, "acc_norm": 0.645320197044335, "acc_norm_stderr": 0.0336612448905145 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.027998073798781657, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.027998073798781657 }, "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": 0.9740932642487047, "acc_stderr": 0.01146452335695318, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.01146452335695318 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7692307692307693, "acc_stderr": 0.021362027725222717, "acc_norm": 0.7692307692307693, "acc_norm_stderr": 0.021362027725222717 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4111111111111111, "acc_stderr": 0.029999923508706675, "acc_norm": 0.4111111111111111, "acc_norm_stderr": 0.029999923508706675 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8319327731092437, "acc_stderr": 0.024289102115692275, "acc_norm": 0.8319327731092437,
