open-llm-leaderboard-old/details_dfurman__llama-2-13b-guanaco-peft
收藏数据集概述
数据集摘要
该数据集是在对模型 dfurman/llama-2-13b-guanaco-peft 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。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，每次运行的详细结果可以在每个配置中找到，使用运行的时间戳作为分割名称。"train" 分割始终指向最新的结果。
数据集结构
数据集由多个配置组成，每个配置包含不同任务的评估结果。每个配置包含多个分割，其中 "train" 分割指向最新的结果。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_dfurman__llama-2-13b-guanaco-peft", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-08-04T16:30:14.703149 运行的最新结果：
python { "all": { "acc": 0.5586096517989027, "acc_stderr": 0.0342928910333228, "acc_norm": 0.5627889461047514, "acc_norm_stderr": 0.034271870197560256, "mc1": 0.29008567931456547, "mc1_stderr": 0.01588623687420952, "mc2": 0.42589160969882056, "mc2_stderr": 0.014357814512818864 }, "harness|arc:challenge|25": { "acc": 0.560580204778157, "acc_stderr": 0.014503747823580122, "acc_norm": 0.5998293515358362, "acc_norm_stderr": 0.014317197787809172 }, "harness|hellaswag|10": { "acc": 0.6170085640310695, "acc_stderr": 0.0048512275270709, "acc_norm": 0.8243377813184625, "acc_norm_stderr": 0.0037975482528516194 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.45185185185185184, "acc_stderr": 0.04299268905480863, "acc_norm": 0.45185185185185184, "acc_norm_stderr": 0.04299268905480863 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5197368421052632, "acc_stderr": 0.04065771002562605, "acc_norm": 0.5197368421052632, "acc_norm_stderr": 0.04065771002562605 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6075471698113207, "acc_stderr": 0.03005258057955785, "acc_norm": 0.6075471698113207, "acc_norm_stderr": 0.03005258057955785 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5902777777777778, "acc_stderr": 0.04112490974670787, "acc_norm": 0.5902777777777778, "acc_norm_stderr": 0.04112490974670787 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.049888765156985884, "acc_norm": 0.44, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4913294797687861, "acc_stderr": 0.038118909889404126, "acc_norm": 0.4913294797687861, "acc_norm_stderr": 0.038118909889404126 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.04336432707993179, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.04336432707993179 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.42127659574468085, "acc_stderr": 0.032278345101462685, "acc_norm": 0.42127659574468085, "acc_norm_stderr": 0.032278345101462685 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.0433913832257986, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.0433913832257986 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728762, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728762 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.024594975128920938, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.024594975128920938 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.041905964388711366, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.041905964388711366 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6774193548387096, "acc_stderr": 0.026593084516572267, "acc_norm": 0.6774193548387096, "acc_norm_stderr": 0.026593084516572267 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43349753694581283, "acc_stderr": 0.03486731727419872, "acc_norm": 0.43349753694581283, "acc_norm_stderr": 0.03486731727419872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6666666666666666, "acc_stderr": 0.0368105086916155, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.0368105086916155 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7070707070707071, "acc_stderr": 0.03242497958178815, "acc_norm": 0.7070707070707071, "acc_norm_stderr": 0.03242497958178815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8341968911917098, "acc_stderr": 0.026839845022314415, "acc_norm": 0.8341968911917098, "acc_norm_stderr": 0.026839845022314415 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5102564102564102, "acc_stderr": 0.025345672221942374, "acc_norm": 0.5102564102564102, "acc_norm_stderr": 0.025345672221942374 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.028037929969114986, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.02803792996911498
