open-llm-leaderboard-old/details_Aryanne__sheared-plus-westlake-nearest-50_75p
收藏数据集概述
数据集简介
该数据集是在模型 Aryanne/sheared-plus-westlake-nearest-50_75p 的评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 数据集包含 63 个配置，每个配置对应一个评估任务。
- 数据集由 1 次运行创建，每次运行的详细信息存储在特定的分割中，分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 额外的 "results" 配置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_Aryanne__sheared-plus-westlake-nearest-50_75p", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-25T04:58:33.658869 运行的最新结果：
python { "all": { "acc": 0.24806262363403858, "acc_stderr": 0.030377724749675428, "acc_norm": 0.2496810641527624, "acc_norm_stderr": 0.0311760528500176, "mc1": 0.2631578947368421, "mc1_stderr": 0.015415241740237012, "mc2": 0.4238910085628728, "mc2_stderr": 0.014960449575853437 }, "harness|arc:challenge|25": { "acc": 0.3310580204778157, "acc_stderr": 0.013752062419817832, "acc_norm": 0.36177474402730375, "acc_norm_stderr": 0.014041957945038083 }, "harness|hellaswag|10": { "acc": 0.43925512846046605, "acc_stderr": 0.0049528205388318855, "acc_norm": 0.5753833897629954, "acc_norm_stderr": 0.004932745013072706 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2518518518518518, "acc_stderr": 0.037498507091740206, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.037498507091740206 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.19736842105263158, "acc_stderr": 0.03238981601699397, "acc_norm": 0.19736842105263158, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21509433962264152, "acc_stderr": 0.02528839450289137, "acc_norm": 0.21509433962264152, "acc_norm_stderr": 0.02528839450289137 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.2, "acc_stderr": 0.04020151261036846, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749874, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749874 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.225531914893617, "acc_stderr": 0.027321078417387533, "acc_norm": 0.225531914893617, "acc_norm_stderr": 0.027321078417387533 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.20899470899470898, "acc_stderr": 0.02094048156533486, "acc_norm": 0.20899470899470898, "acc_norm_stderr": 0.02094048156533486 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.0404061017820884, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0404061017820884 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.20967741935483872, "acc_stderr": 0.02315787934908353, "acc_norm": 0.20967741935483872, "acc_norm_stderr": 0.02315787934908353 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.1625615763546798, "acc_stderr": 0.025960300064605594, "acc_norm": 0.1625615763546798, "acc_norm_stderr": 0.025960300064605594 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.03501438706296781, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.17676767676767677, "acc_stderr": 0.027178752639044915, "acc_norm": 0.17676767676767677, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.24352331606217617, "acc_stderr": 0.030975436386845447, "acc_norm": 0.24352331606217617, "acc_norm_stderr": 0.030975436386845447 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.24871794871794872, "acc_stderr": 0.0219169577092138, "acc_norm": 0.24871794871794872, "acc_norm_stderr": 0.0219169577092138 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.22592592592592592, "acc_stderr": 0.0254975326396
