open-llm-leaderboard-old/details_ibivibiv__strix-rufipes-70b
收藏数据集概述
该数据集是在模型 ibivibiv/strix-rufipes-70b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集组成
- 数据集包含 63 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。
- 一个额外的配置 "results" 存储所有运行的聚合结果，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_ibivibiv__strix-rufipes-70b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-23T03:56:38.126146 运行的最新结果：
python { "all": { "acc": 0.6910894247381432, "acc_stderr": 0.03074765419800289, "acc_norm": 0.6948907257668793, "acc_norm_stderr": 0.03135484817423871, "mc1": 0.40024479804161567, "mc1_stderr": 0.01715160555574914, "mc2": 0.5672072620719157, "mc2_stderr": 0.014748654287331589 }, "harness|arc:challenge|25": { "acc": 0.674061433447099, "acc_stderr": 0.013697432466693246, "acc_norm": 0.7133105802047781, "acc_norm_stderr": 0.013214986329274777 }, "harness|hellaswag|10": { "acc": 0.6898028281218881, "acc_stderr": 0.004616288245259753, "acc_norm": 0.8786098386775543, "acc_norm_stderr": 0.003259127057668171 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6370370370370371, "acc_stderr": 0.04153948404742399, "acc_norm": 0.6370370370370371, "acc_norm_stderr": 0.04153948404742399 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7960526315789473, "acc_stderr": 0.032790004063100515, "acc_norm": 0.7960526315789473, "acc_norm_stderr": 0.032790004063100515 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.04461960433384741, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7169811320754716, "acc_stderr": 0.027724236492700918, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700918 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8125, "acc_stderr": 0.032639560491693344, "acc_norm": 0.8125, "acc_norm_stderr": 0.032639560491693344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "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": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6851063829787234, "acc_stderr": 0.03036358219723817, "acc_norm": 0.6851063829787234, "acc_norm_stderr": 0.03036358219723817 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.0470070803355104, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.0470070803355104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.0411391498118926, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41534391534391535, "acc_stderr": 0.025379524910778387, "acc_norm": 0.41534391534391535, "acc_norm_stderr": 0.025379524910778387 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8064516129032258, "acc_stderr": 0.022475258525536057, "acc_norm": 0.8064516129032258, "acc_norm_stderr": 0.022475258525536057 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.02845038880528437, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.02845038880528437 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8787878787878788, "acc_stderr": 0.023253157951942088, "acc_norm": 0.8787878787878788, "acc_norm_stderr": 0.023253157951942088 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9326424870466321, "acc_stderr": 0.018088393839078912, "acc_norm": 0.9326424870466321, "acc_norm_stderr": 0.018088393839078912 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.717948717948718, "acc_stderr": 0.0228158130988966, "acc_norm": 0.717948717948718, "acc_norm_stderr": 0.0228158130988966 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2962962962962963, "acc_stderr": 0.027840811495871923, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.027840811495871923 },
