open-llm-leaderboard-old/details_Azure99__blossom-v5-9b
收藏数据集概述
数据集简介
该数据集是在对模型 Azure99/blossom-v5-9b 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。
数据集加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Azure99__blossom-v5-9b", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 run 2024-03-21T15:37:03.039241 的摘要：
python { "all": { "acc": 0.6922699632968013, "acc_stderr": 0.03083140719752146, "acc_norm": 0.6983143460865201, "acc_norm_stderr": 0.03142412981235352, "mc1": 0.35862913096695226, "mc1_stderr": 0.016789289499502025, "mc2": 0.5278235105912508, "mc2_stderr": 0.015439131046987332 }, "harness|arc:challenge|25": { "acc": 0.5972696245733788, "acc_stderr": 0.014332236306790145, "acc_norm": 0.6245733788395904, "acc_norm_stderr": 0.014150631435111728 }, "harness|hellaswag|10": { "acc": 0.5924118701453893, "acc_stderr": 0.004903815885983279, "acc_norm": 0.784106751643099, "acc_norm_stderr": 0.004105997149954855 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.042561937679014075, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.042561937679014075 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7828947368421053, "acc_stderr": 0.03355045304882924, "acc_norm": 0.7828947368421053, "acc_norm_stderr": 0.03355045304882924 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7245283018867924, "acc_stderr": 0.027495663683724057, "acc_norm": 0.7245283018867924, "acc_norm_stderr": 0.027495663683724057 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.03476590104304134, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6994219653179191, "acc_stderr": 0.0349610148119118, "acc_norm": 0.6994219653179191, "acc_norm_stderr": 0.0349610148119118 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.048971049527263666, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165065, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6978723404255319, "acc_stderr": 0.030017554471880557, "acc_norm": 0.6978723404255319, "acc_norm_stderr": 0.030017554471880557 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.046570472605949646, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.046570472605949646 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6896551724137931, "acc_stderr": 0.03855289616378949, "acc_norm": 0.6896551724137931, "acc_norm_stderr": 0.03855289616378949 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5687830687830688, "acc_stderr": 0.025506481698138215, "acc_norm": 0.5687830687830688, "acc_norm_stderr": 0.025506481698138215 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6111111111111112, "acc_stderr": 0.04360314860077459, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8387096774193549, "acc_stderr": 0.020923327006423294, "acc_norm": 0.8387096774193549, "acc_norm_stderr": 0.020923327006423294 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5517241379310345, "acc_stderr": 0.03499113137676744, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.03499113137676744 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.84, "acc_stderr": 0.03684529491774707, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774707 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8303030303030303, "acc_stderr": 0.029311188674983106, "acc_norm": 0.8303030303030303, "acc_norm_stderr": 0.029311188674983106 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8787878787878788, "acc_stderr": 0.023253157951942084, "acc_norm": 0.8787878787878788, "acc_norm_stderr": 0.023253157951942084 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9222797927461139, "acc_stderr": 0.019321805557223147, "acc_norm": 0.9222797927461139, "acc_norm_stderr": 0.019321805557223147 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.764102564102564, "acc_stderr": 0.021525965407408726, "acc_norm": 0.764102564102564, "acc_norm_stderr": 0.021525965407408726 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4666666666666667, "acc_stderr": 0.03041771696171748, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.03041771696171748 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.82352
