open-llm-leaderboard-old/details_TheBloke__Project-Baize-v2-13B-GPTQ
收藏数据集概述
数据集简介
该数据集是在对模型 TheBloke/Project-Baize-v2-13B-GPTQ 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集由 60 个配置组成，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" 分割始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_TheBloke__Project-Baize-v2-13B-GPTQ", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-08-22T13:47:48.408564 运行的最新结果：
python { "all": { "acc": 0.2587648736963, "acc_stderr": 0.03187184494961934, "acc_norm": 0.2594229387695995, "acc_norm_stderr": 0.03188074586823278, "mc1": 0.24112607099143207, "mc1_stderr": 0.014974827279752339, "mc2": 0.48217112656241606, "mc2_stderr": 0.01706048623340291 }, "harness|arc:challenge|25": { "acc": 0.24573378839590443, "acc_stderr": 0.01258103345373011, "acc_norm": 0.27559726962457337, "acc_norm_stderr": 0.013057169655761838 }, "harness|hellaswag|10": { "acc": 0.2552280422226648, "acc_stderr": 0.004350982826580599, "acc_norm": 0.26419040031866164, "acc_norm_stderr": 0.004400000822742062 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04072314811876837, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.24342105263157895, "acc_stderr": 0.034923496688842384, "acc_norm": 0.24342105263157895, "acc_norm_stderr": 0.034923496688842384 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.20754716981132076, "acc_stderr": 0.02495991802891127, "acc_norm": 0.20754716981132076, "acc_norm_stderr": 0.02495991802891127 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2254335260115607, "acc_stderr": 0.03186209851641143, "acc_norm": 0.2254335260115607, "acc_norm_stderr": 0.03186209851641143 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.043364327079931785, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.043364327079931785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2765957446808511, "acc_stderr": 0.02924188386962881, "acc_norm": 0.2765957446808511, "acc_norm_stderr": 0.02924188386962881 }, "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": 0.2689655172413793, "acc_stderr": 0.03695183311650232, "acc_norm": 0.2689655172413793, "acc_norm_stderr": 0.03695183311650232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24074074074074073, "acc_stderr": 0.0220190800122179, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.0220190800122179 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.038095238095238106, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.038095238095238106 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.23225806451612904, "acc_stderr": 0.02402225613030824, "acc_norm": 0.23225806451612904, "acc_norm_stderr": 0.02402225613030824 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2857142857142857, "acc_stderr": 0.03178529710642751, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.03178529710642751 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.26666666666666666, "acc_stderr": 0.03453131801885415, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03453131801885415 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25757575757575757, "acc_stderr": 0.03115626951964686, "acc_norm": 0.25757575757575757, "acc_norm_stderr": 0.03115626951964686 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.20207253886010362, "acc_stderr": 0.02897908979429673, "acc_norm": 0.20207253886010362, "acc_norm_stderr": 0.02897908979429673 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2128205128205128, "acc_stderr": 0.02075242372212802, "acc_norm": 0.2128205128205128, "acc_norm_stderr": 0.02075242372212802 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340492, "acc
