open-llm-leaderboard-old/details_Menouar__gemma-2b-chat-ultra
收藏数据集概述
该数据集是在对模型 Menouar/gemma-2b-chat-ultra 进行评估运行时自动创建的，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，每个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" 分割总是指向最新的结果。
- 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_Menouar__gemma-2b-chat-ultra", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-22T02:35:53.241150 运行的最新结果：
python { "all": { "acc": 0.3957913300987599, "acc_stderr": 0.03417582131557158, "acc_norm": 0.3986889029486514, "acc_norm_stderr": 0.03492975956849049, "mc1": 0.2594859241126071, "mc1_stderr": 0.015345409485557982, "mc2": 0.3906683350216857, "mc2_stderr": 0.014343622966056763 }, "harness|arc:challenge|25": { "acc": 0.4684300341296928, "acc_stderr": 0.014582236460866973, "acc_norm": 0.48293515358361777, "acc_norm_stderr": 0.014602878388536593 }, "harness|hellaswag|10": { "acc": 0.523401712806214, "acc_stderr": 0.0049843132057914375, "acc_norm": 0.7017526389165505, "acc_norm_stderr": 0.0045655368086325535 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4148148148148148, "acc_stderr": 0.042561937679014075, "acc_norm": 0.4148148148148148, "acc_norm_stderr": 0.042561937679014075 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3684210526315789, "acc_stderr": 0.03925523381052932, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.03925523381052932 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4716981132075472, "acc_stderr": 0.0307235352490061, "acc_norm": 0.4716981132075472, "acc_norm_stderr": 0.0307235352490061 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4305555555555556, "acc_stderr": 0.04140685639111502, "acc_norm": 0.4305555555555556, "acc_norm_stderr": 0.04140685639111502 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.45664739884393063, "acc_stderr": 0.03798106566014499, "acc_norm": 0.45664739884393063, "acc_norm_stderr": 0.03798106566014499 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.13725490196078433, "acc_stderr": 0.034240846698915195, "acc_norm": 0.13725490196078433, "acc_norm_stderr": 0.034240846698915195 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.39574468085106385, "acc_stderr": 0.031967586978353627, "acc_norm": 0.39574468085106385, "acc_norm_stderr": 0.031967586978353627 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374767, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374767 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.46206896551724136, "acc_stderr": 0.041546596717075474, "acc_norm": 0.46206896551724136, "acc_norm_stderr": 0.041546596717075474 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25132275132275134, "acc_stderr": 0.022340482339643895, "acc_norm": 0.25132275132275134, "acc_norm_stderr": 0.022340482339643895 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3412698412698413, "acc_stderr": 0.04240799327574924, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.04240799327574924 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4161290322580645, "acc_stderr": 0.028040981380761554, "acc_norm": 0.4161290322580645, "acc_norm_stderr": 0.028040981380761554 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3251231527093596, "acc_stderr": 0.032957975663112704, "acc_norm": 0.3251231527093596, "acc_norm_stderr": 0.032957975663112704 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.41818181818181815, "acc_stderr": 0.03851716319398394, "acc_norm": 0.41818181818181815, "acc_norm_stderr": 0.03851716319398394 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.494949494949495, "acc_stderr": 0.035621707606254015, "acc_norm": 0.494949494949495, "acc_norm_stderr": 0.035621707606254015 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5181347150259067, "acc_stderr": 0.036060650018329185, "acc_norm": 0.5181347150259067, "acc_norm_stderr": 0.036060650018329185 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3769230769230769, "acc_stderr": 0.024570975364225995, "acc_norm": 0.3769230769230769, "acc_norm_stderr": 0.024570975364225995 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24074074074074073, "acc_stderr": 0.026067159222275777, "acc_norm": 0.240740740740
