open-llm-leaderboard-old/details_codellama__CodeLlama-70b-Instruct-hf
收藏数据集概述
数据集摘要
该数据集是在对模型 codellama/CodeLlama-70b-Instruct-hf 进行评估运行期间自动创建的，评估结果展示在 Open LLM Leaderboard 上。
数据集组成
数据集由 63 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，每次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。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_codellama__CodeLlama-70b-Instruct-hf", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 2024-02-02T06:15:21.306042 的摘要： python { "all": { "acc": 0.5648604524571269, "acc_stderr": 0.03399038244243267, "acc_norm": 0.5673299922382132, "acc_norm_stderr": 0.034688595336715734, "mc1": 0.3525091799265606, "mc1_stderr": 0.016724646380756544, "mc2": 0.5044393244952377, "mc2_stderr": 0.015451705191766632 }, "harness|arc:challenge|25": { "acc": 0.5179180887372014, "acc_stderr": 0.014602005585490982, "acc_norm": 0.5503412969283277, "acc_norm_stderr": 0.014537144444284741 }, "harness|hellaswag|10": { "acc": 0.5812587134037045, "acc_stderr": 0.0049234456278615234, "acc_norm": 0.7723561043616809, "acc_norm_stderr": 0.00418454567538735 }, "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": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5723684210526315, "acc_stderr": 0.04026097083296562, "acc_norm": 0.5723684210526315, "acc_norm_stderr": 0.04026097083296562 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.539622641509434, "acc_stderr": 0.030676096599389177, "acc_norm": 0.539622641509434, "acc_norm_stderr": 0.030676096599389177 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5208333333333334, "acc_stderr": 0.04177578950739993, "acc_norm": 0.5208333333333334, "acc_norm_stderr": 0.04177578950739993 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.48554913294797686, "acc_stderr": 0.03810871630454764, "acc_norm": 0.48554913294797686, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077636, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077636 }, "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": 0.5234042553191489, "acc_stderr": 0.03265019475033582, "acc_norm": 0.5234042553191489, "acc_norm_stderr": 0.03265019475033582 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.42105263157894735, "acc_stderr": 0.046446020912223177, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.041546596717075474, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.041546596717075474 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42857142857142855, "acc_stderr": 0.025487187147859375, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.025487187147859375 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.044444444444444495, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.044444444444444495 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.635483870967742, "acc_stderr": 0.02737987122994325, "acc_norm": 0.635483870967742, "acc_norm_stderr": 0.02737987122994325 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39408866995073893, "acc_stderr": 0.034381579670365446, "acc_norm": 0.39408866995073893, "acc_norm_stderr": 0.034381579670365446 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.73, "acc_stderr": 0.044619604333847394, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7333333333333333, "acc_stderr": 0.03453131801885417, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885417 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.702020202020202, "acc_stderr": 0.03258630383836556, "acc_norm": 0.702020202020202, "acc_norm_stderr": 0.03258630383836556 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7875647668393783, "acc_stderr": 0.02951928261681723, "acc_norm": 0.7875647668393783, "acc_norm_stderr": 0.02951928261681723 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5230769230769231, "acc_stderr": 0.025323990861736232, "acc_norm": 0.5230769230769231, "acc_norm_stderr": 0.025323990861736232 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.362962962962963, "acc_stderr": 0.02931820364520686, "acc_norm": 0
