open-llm-leaderboard-old/details_grimpep__llama2-22B-GPLATTY
收藏数据集概述
该数据集是在模型 grimpep/llama2-22B-GPLATTY 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集组成
- 数据集包含 61 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。
- 额外的 "results" 配置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_grimpep__llama2-22B-GPLATTY", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-08-17T14:31:52.312230 运行的最新结果：
python { "all": { "acc": 0.5471453447112705, "acc_stderr": 0.034452241209601206, "acc_norm": 0.550874294679223, "acc_norm_stderr": 0.03443332656790291, "mc1": 0.31334149326805383, "mc1_stderr": 0.0162380650690596, "mc2": 0.4692973392633332, "mc2_stderr": 0.0156700439246235 }, "harness|arc:challenge|25": { "acc": 0.560580204778157, "acc_stderr": 0.014503747823580123, "acc_norm": 0.5895904436860068, "acc_norm_stderr": 0.014374922192642662 }, "harness|hellaswag|10": { "acc": 0.6290579565823541, "acc_stderr": 0.004820697457420421, "acc_norm": 0.8200557657837084, "acc_norm_stderr": 0.003833559228158675 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411022, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411022 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5723684210526315, "acc_stderr": 0.04026097083296564, "acc_norm": 0.5723684210526315, "acc_norm_stderr": 0.04026097083296564 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5924528301886792, "acc_stderr": 0.03024223380085449, "acc_norm": 0.5924528301886792, "acc_norm_stderr": 0.03024223380085449 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6319444444444444, "acc_stderr": 0.04032999053960718, "acc_norm": 0.6319444444444444, "acc_norm_stderr": 0.04032999053960718 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.48554913294797686, "acc_stderr": 0.03810871630454764, "acc_norm": 0.48554913294797686, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.042801058373643966, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.042801058373643966 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4425531914893617, "acc_stderr": 0.03246956919789958, "acc_norm": 0.4425531914893617, "acc_norm_stderr": 0.03246956919789958 }, "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": 0.503448275862069, "acc_stderr": 0.04166567577101579, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.04166567577101579 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3306878306878307, "acc_stderr": 0.024229965298425082, "acc_norm": 0.3306878306878307, "acc_norm_stderr": 0.024229965298425082 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6258064516129033, "acc_stderr": 0.027528904299845697, "acc_norm": 0.6258064516129033, "acc_norm_stderr": 0.027528904299845697 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4433497536945813, "acc_stderr": 0.03495334582162934, "acc_norm": 0.4433497536945813, "acc_norm_stderr": 0.03495334582162934 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6484848484848484, "acc_stderr": 0.037282069986826503, "acc_norm": 0.6484848484848484, "acc_norm_stderr": 0.037282069986826503 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6818181818181818, "acc_stderr": 0.03318477333845331, "acc_norm": 0.6818181818181818, "acc_norm_stderr": 0.03318477333845331 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7927461139896373, "acc_stderr": 0.02925282329180363, "acc_norm": 0.7927461139896373, "acc_norm_stderr": 0.02925282329180363 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5307692307692308, "acc_stderr": 0.025302958890850154, "acc_norm": 0.5307692307692308, "acc_norm_stderr": 0.025302958890850154 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085622, "acc_norm": 0.2740740740740741, "acc_norm_
