open-llm-leaderboard-old/details_codellama__CodeLlama-34b-Python-hf
收藏数据集概述
数据集简介
该数据集是在评估模型 codellama/CodeLlama-34b-Python-hf 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集结构
- 数据集包含 64 个配置，每个配置对应一个评估任务。
- 数据集由 4 次运行结果组成，每次运行的结果可以在每个配置中找到，以运行的时间戳命名的特定分片形式存储。
- "train" 分片始终指向最新的结果。
额外配置
- 一个名为 "results" 的额外配置存储了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_codellama__CodeLlama-34b-Python-hf", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-19T02:11:34.305471 运行的最新结果：
python { "all": { "acc": 0.4928401323448239, "acc_stderr": 0.03436384457050625, "acc_norm": 0.4959176673909788, "acc_norm_stderr": 0.03508471975074113, "mc1": 0.2717258261933905, "mc1_stderr": 0.01557284045287583, "mc2": 0.4137349714821021, "mc2_stderr": 0.014581913837481237 }, "harness|arc:challenge|25": { "acc": 0.4684300341296928, "acc_stderr": 0.01458223646086698, "acc_norm": 0.5042662116040956, "acc_norm_stderr": 0.014610858923956955 }, "harness|hellaswag|10": { "acc": 0.5615415255925115, "acc_stderr": 0.004951840978219683, "acc_norm": 0.7635929097789285, "acc_norm_stderr": 0.004240066898702514 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.045126085985421296, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421296 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.37777777777777777, "acc_stderr": 0.04188307537595853, "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.04188307537595853 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.46710526315789475, "acc_stderr": 0.040601270352363966, "acc_norm": 0.46710526315789475, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5132075471698113, "acc_stderr": 0.030762134874500476, "acc_norm": 0.5132075471698113, "acc_norm_stderr": 0.030762134874500476 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4791666666666667, "acc_stderr": 0.04177578950739993, "acc_norm": 0.4791666666666667, "acc_norm_stderr": 0.04177578950739993 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4277456647398844, "acc_stderr": 0.03772446857518026, "acc_norm": 0.4277456647398844, "acc_norm_stderr": 0.03772446857518026 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808778, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808778 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3829787234042553, "acc_stderr": 0.031778212502369216, "acc_norm": 0.3829787234042553, "acc_norm_stderr": 0.031778212502369216 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.04462917535336936, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.04462917535336936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.02459497512892094, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.02459497512892094 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5225806451612903, "acc_stderr": 0.02841498501970786, "acc_norm": 0.5225806451612903, "acc_norm_stderr": 0.02841498501970786 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3448275862068966, "acc_stderr": 0.033442837442804574, "acc_norm": 0.3448275862068966, "acc_norm_stderr": 0.033442837442804574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6, "acc_stderr": 0.038254602783800246, "acc_norm": 0.6, "acc_norm_stderr": 0.038254602783800246 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6060606060606061, "acc_stderr": 0.034812853382329624, "acc_norm": 0.6060606060606061, "acc_norm_stderr": 0.034812853382329624 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7046632124352331, "acc_stderr": 0.032922966391551414, "acc_norm": 0.7046632124352331, "acc_norm_stderr": 0.032922966391551414 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.45384615384615384, "acc_stderr": 0.025242770987126177, "acc_norm": 0.45384615384615384, "acc_norm_stderr": 0.025242770987126177 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.028493465091028597, "acc_norm": 0.32222222222222224, "acc_norm_stderr": 0
