open-llm-leaderboard-old/details_abacusai__MM-OV-bagel-DPO-34b-c1000-250
收藏数据集概述
数据集简介
该数据集是在评估模型abacusai/MM-OV-bagel-DPO-34b-c1000-250在Open LLM Leaderboard上的运行过程中自动创建的。
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2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"分割始终指向最新结果。
额外配置
一个额外的配置"results"存储所有运行的聚合结果，用于计算和显示在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_abacusai__MM-OV-bagel-DPO-34b-c1000-250", "harness_winogrande_5", split="train")
最新结果
以下是最新结果： python { "all": { "acc": 0.7597155366563035, "acc_stderr": 0.02837032363320797, "acc_norm": 0.7632345413090461, "acc_norm_stderr": 0.02891633054739416, "mc1": 0.4810281517747858, "mc1_stderr": 0.01749089640576235, "mc2": 0.6367417890283518, "mc2_stderr": 0.01475171297078638 }, "harness|arc:challenge|25": { "acc": 0.6459044368600683, "acc_stderr": 0.01397545412275656, "acc_norm": 0.681740614334471, "acc_norm_stderr": 0.013611993916971451 }, "harness|hellaswag|10": { "acc": 0.6408086038637721, "acc_stderr": 0.004787829168255652, "acc_norm": 0.8396733718382793, "acc_norm_stderr": 0.0036615885079775523 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7481481481481481, "acc_stderr": 0.03749850709174021, "acc_norm": 0.7481481481481481, "acc_norm_stderr": 0.03749850709174021 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8881578947368421, "acc_stderr": 0.02564834125169361, "acc_norm": 0.8881578947368421, "acc_norm_stderr": 0.02564834125169361 }, "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": 0.8075471698113208, "acc_stderr": 0.024262979839372274, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9097222222222222, "acc_stderr": 0.023964965777906935, "acc_norm": 0.9097222222222222, "acc_norm_stderr": 0.023964965777906935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7398843930635838, "acc_stderr": 0.03345036916788991, "acc_norm": 0.7398843930635838, "acc_norm_stderr": 0.03345036916788991 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5392156862745098, "acc_stderr": 0.04959859966384181, "acc_norm": 0.5392156862745098, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036845, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7829787234042553, "acc_stderr": 0.02694748312149625, "acc_norm": 0.7829787234042553, "acc_norm_stderr": 0.02694748312149625 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5964912280701754, "acc_stderr": 0.04615186962583707, "acc_norm": 0.5964912280701754, "acc_norm_stderr": 0.04615186962583707 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7517241379310344, "acc_stderr": 0.036001056927277696, "acc_norm": 0.7517241379310344, "acc_norm_stderr": 0.036001056927277696 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7407407407407407, "acc_stderr": 0.02256989707491842, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.02256989707491842 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5317460317460317, "acc_stderr": 0.04463112720677173, "acc_norm": 0.5317460317460317, "acc_norm_stderr": 0.04463112720677173 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9, "acc_stderr": 0.01706640371965727, "acc_norm": 0.9, "acc_norm_stderr": 0.01706640371965727 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6798029556650246, "acc_stderr": 0.03282649385304151, "acc_norm": 0.6798029556650246, "acc_norm_stderr": 0.03282649385304151 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8484848484848485, "acc_stderr": 0.027998073798781664, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.027998073798781664 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9444444444444444, "acc_stderr": 0.016319950700767374, "acc_norm": 0.9444444444444444, "acc_norm_stderr": 0.016319950700767374 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9637305699481865, "acc_stderr": 0.013492659751295131, "acc_norm": 0.9637305699481865, "acc_norm_stderr": 0.013492659751295131 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8102564102564103, "acc_stderr": 0.0198801654065888, "acc_norm": 0.8102564102564103, "acc_norm_stderr": 0.0198801654065888 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.45555555555555555, "acc_stderr": 0.03036486250482443, "acc_norm": 0.45555555555555555, "acc_norm_stderr": 0.03036486250482443 },
