open-llm-leaderboard-old/details_kyujinpy__PlatYi-34B-LoRA
收藏数据集概述
数据集摘要
该数据集是在评估模型 kyujinpy/PlatYi-34B-LoRA 在 Open LLM Leaderboard 上的自动创建的。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 个配置
- 数据来源：从 1 次运行中创建
- 数据分割：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割指向最新结果。
- 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_kyujinpy__PlatYi-34B-LoRA", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-05T00:53:53.251371 运行的最新结果：
python { "all": { "acc": 0.774827191806162, "acc_stderr": 0.027570240573755966, "acc_norm": 0.7838406442171528, "acc_norm_stderr": 0.028074245588194685, "mc1": 0.3733170134638923, "mc1_stderr": 0.01693237055757063, "mc2": 0.5332425206331443, "mc2_stderr": 0.014839740435159312 }, "harness|arc:challenge|25": { "acc": 0.643344709897611, "acc_stderr": 0.013998056902620189, "acc_norm": 0.6715017064846417, "acc_norm_stderr": 0.013724978465537297 }, "harness|hellaswag|10": { "acc": 0.6567416849233221, "acc_stderr": 0.00473826494473715, "acc_norm": 0.8537143995220076, "acc_norm_stderr": 0.003526700741879443 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7555555555555555, "acc_stderr": 0.03712537833614866, "acc_norm": 0.7555555555555555, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8947368421052632, "acc_stderr": 0.024974533450920697, "acc_norm": 0.8947368421052632, "acc_norm_stderr": 0.024974533450920697 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.81, "acc_stderr": 0.03942772444036623, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8, "acc_stderr": 0.02461829819586651, "acc_norm": 0.8, "acc_norm_stderr": 0.02461829819586651 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8958333333333334, "acc_stderr": 0.025545239210256917, "acc_norm": 0.8958333333333334, "acc_norm_stderr": 0.025545239210256917 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252606, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.45, "acc_stderr": 0.04999999999999999, "acc_norm": 0.45, "acc_norm_stderr": 0.04999999999999999 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7398843930635838, "acc_stderr": 0.03345036916788991, "acc_norm": 0.7398843930635838, "acc_norm_stderr": 0.03345036916788991 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5686274509803921, "acc_stderr": 0.04928099597287534, "acc_norm": 0.5686274509803921, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.82, "acc_stderr": 0.03861229196653694, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7957446808510639, "acc_stderr": 0.026355158413349424, "acc_norm": 0.7957446808510639, "acc_norm_stderr": 0.026355158413349424 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5789473684210527, "acc_stderr": 0.046446020912223177, "acc_norm": 0.5789473684210527, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8137931034482758, "acc_stderr": 0.03243946159004616, "acc_norm": 0.8137931034482758, "acc_norm_stderr": 0.03243946159004616 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7380952380952381, "acc_stderr": 0.02264421261552521, "acc_norm": 0.7380952380952381, "acc_norm_stderr": 0.02264421261552521 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5873015873015873, "acc_stderr": 0.04403438954768176, "acc_norm": 0.5873015873015873, "acc_norm_stderr": 0.04403438954768176 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9161290322580645, "acc_stderr": 0.015769027496775667, "acc_norm": 0.9161290322580645, "acc_norm_stderr": 0.015769027496775667 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6699507389162561, "acc_stderr": 0.033085304262282574, "acc_norm": 0.6699507389162561, "acc_norm_stderr": 0.033085304262282574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.87, "acc_stderr": 0.03379976689896309, "acc_norm": 0.87, "acc_norm_stderr": 0.03379976689896309 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8666666666666667, "acc_stderr": 0.026544435312706473, "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.026544435312706473 }, "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": 0.9689119170984456, "acc_stderr": 0.012525310625527033, "acc_norm": 0.9689119170984456, "acc_norm_stderr": 0.012525310625527033 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8256410256410256, "acc_stderr": 0.01923724980340523, "acc_norm": 0.8256410256410256, "acc_norm_stderr": 0.01923724980340523 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4740740740740741, "acc_stderr": 0.03044452852881074, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.0304445
