open-llm-leaderboard-old/details_OpenBuddy__openbuddy-deepseekcoder-33b-v16.1-32k
收藏数据集概述
数据集简介
该数据集是在模型OpenBuddy/openbuddy-deepseekcoder-33b-v16.1-32k的评估运行期间自动创建的，用于Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集从2次运行中创建。每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 最新结果："train"分割始终指向最新的结果。
- 结果汇总：一个额外的配置"results"存储所有运行的汇总结果，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_OpenBuddy__openbuddy-deepseekcoder-33b-v16.1-32k", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-08T05:49:52.384662运行的最新结果：
python { "all": { "acc": 0.4353450707475209, "acc_stderr": 0.03461671516845463, "acc_norm": 0.43568385204742693, "acc_norm_stderr": 0.035330423938582683, "mc1": 0.2962056303549572, "mc1_stderr": 0.015983595101811392, "mc2": 0.44491612521505014, "mc2_stderr": 0.014935356559440623 }, "harness|arc:challenge|25": { "acc": 0.39334470989761094, "acc_stderr": 0.014275101465693024, "acc_norm": 0.45051194539249145, "acc_norm_stderr": 0.014539646098471627 }, "harness|hellaswag|10": { "acc": 0.45717984465245964, "acc_stderr": 0.004971449552787173, "acc_norm": 0.6079466241784505, "acc_norm_stderr": 0.0048721072620824726 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.362962962962963, "acc_stderr": 0.041539484047424, "acc_norm": 0.362962962962963, "acc_norm_stderr": 0.041539484047424 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4144736842105263, "acc_stderr": 0.04008973785779204, "acc_norm": 0.4144736842105263, "acc_norm_stderr": 0.04008973785779204 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.39622641509433965, "acc_stderr": 0.030102793781791194, "acc_norm": 0.39622641509433965, "acc_norm_stderr": 0.030102793781791194 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3472222222222222, "acc_stderr": 0.0398124054371786, "acc_norm": 0.3472222222222222, "acc_norm_stderr": 0.0398124054371786 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.34104046242774566, "acc_stderr": 0.03614665424180826, "acc_norm": 0.34104046242774566, "acc_norm_stderr": 0.03614665424180826 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.41702127659574467, "acc_stderr": 0.032232762667117124, "acc_norm": 0.41702127659574467, "acc_norm_stderr": 0.032232762667117124 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.37719298245614036, "acc_stderr": 0.04559522141958216, "acc_norm": 0.37719298245614036, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728763, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.35714285714285715, "acc_stderr": 0.02467786284133278, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.02467786284133278 }, "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": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.44193548387096776, "acc_stderr": 0.02825155790684974, "acc_norm": 0.44193548387096776, "acc_norm_stderr": 0.02825155790684974 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3103448275862069, "acc_stderr": 0.032550867699701024, "acc_norm": 0.3103448275862069, "acc_norm_stderr": 0.032550867699701024 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5212121212121212, "acc_stderr": 0.03900828913737302, "acc_norm": 0.5212121212121212, "acc_norm_stderr": 0.03900828913737302 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4696969696969697, "acc_stderr": 0.03555804051763929, "acc_norm": 0.4696969696969697, "acc_norm_stderr": 0.03555804051763929 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.42487046632124353, "acc_stderr": 0.0356747133521254, "acc_norm": 0.42487046632124353, "acc_norm_stderr": 0.0356747133521254 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.34102564102564104, "acc_stderr": 0.02403548967633506, "acc_norm": 0.34102564102564104, "acc_norm_stderr": 0.02403548967633506 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224,
