open-llm-leaderboard-old/details_Charlie911__MultiLoRA-mmlu
收藏数据集概述
该数据集是在对模型 Charlie911/MultiLoRA-mmlu 进行评估运行期间自动创建的，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_Charlie911__MultiLoRA-mmlu", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-02T00:16:37.919745 运行的最新结果：
python { "all": { "acc": 0.49682393519091933, "acc_stderr": 0.034234549326781244, "acc_norm": 0.5024513039750834, "acc_norm_stderr": 0.03499839555197597, "mc1": 0.3268053855569155, "mc1_stderr": 0.01641987473113503, "mc2": 0.5020042655317223, "mc2_stderr": 0.015409102519026984 }, "harness|arc:challenge|25": { "acc": 0.49658703071672355, "acc_stderr": 0.014611050403244077, "acc_norm": 0.5238907849829352, "acc_norm_stderr": 0.014594701798071654 }, "harness|hellaswag|10": { "acc": 0.5803624775941048, "acc_stderr": 0.004924910433106353, "acc_norm": 0.7720573590918144, "acc_norm_stderr": 0.0041864806453155625 }, "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": 0.45185185185185184, "acc_stderr": 0.04299268905480864, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.04299268905480864 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.506578947368421, "acc_stderr": 0.040685900502249704, "acc_norm": 0.506578947368421, "acc_norm_stderr": 0.040685900502249704 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5169811320754717, "acc_stderr": 0.030755120364119905, "acc_norm": 0.5169811320754717, "acc_norm_stderr": 0.030755120364119905 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5, "acc_stderr": 0.04181210050035455, "acc_norm": 0.5, "acc_norm_stderr": 0.04181210050035455 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.43352601156069365, "acc_stderr": 0.03778621079092055, "acc_norm": 0.43352601156069365, "acc_norm_stderr": 0.03778621079092055 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03708284662416542, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03708284662416542 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.43829787234042555, "acc_stderr": 0.032436186361081004, "acc_norm": 0.43829787234042555, "acc_norm_stderr": 0.032436186361081004 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159393, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159393 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2857142857142857, "acc_stderr": 0.023266512213730578, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.023266512213730578 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.04190596438871136, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.04190596438871136 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.535483870967742, "acc_stderr": 0.02837228779796293, "acc_norm": 0.535483870967742, "acc_norm_stderr": 0.02837228779796293 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39901477832512317, "acc_stderr": 0.03445487686264715, "acc_norm": 0.39901477832512317, "acc_norm_stderr": 0.03445487686264715 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6303030303030303, "acc_stderr": 0.03769430314512567, "acc_norm": 0.6303030303030303, "acc_norm_stderr": 0.03769430314512567 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5909090909090909, "acc_stderr": 0.03502975799413007, "acc_norm": 0.5909090909090909, "acc_norm_stderr": 0.03502975799413007 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7046632124352331, "acc_stderr": 0.03292296639155141, "acc_norm": 0.7046632124352331, "acc_norm_stderr": 0.03292296639155141 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4717948717948718, "acc_stderr": 0.025310639254933893, "acc_norm": 0.4717948717948718, "acc_norm_stderr": 0.025310639254933893 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24074074074074073, "acc_stderr": 0.026067159222275805, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.026067159222275805 }, "harness|hendrycks
