open-llm-leaderboard-old/details_ewqr2130__llama2-7b-raw-sft
收藏数据集概述
数据集简介
该数据集是在评估模型 ewqr2130/llama2-7b-raw-sft 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，每个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。
额外配置
一个额外的配置 "results" 存储了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_ewqr2130__llama2-7b-raw-sft", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-10T15:15:16.030532 运行的最新结果：
python { "all": { "acc": 0.3451686041304389, "acc_stderr": 0.033177024770114395, "acc_norm": 0.34794617103590064, "acc_norm_stderr": 0.033992606612009306, "mc1": 0.2521419828641371, "mc1_stderr": 0.015201522246299963, "mc2": 0.4077071941467522, "mc2_stderr": 0.014214727907656348 }, "harness|arc:challenge|25": { "acc": 0.43430034129692835, "acc_stderr": 0.01448470304885736, "acc_norm": 0.47440273037542663, "acc_norm_stderr": 0.014592230885298964 }, "harness|hellaswag|10": { "acc": 0.5518820952001593, "acc_stderr": 0.004962846206125493, "acc_norm": 0.7525393347938658, "acc_norm_stderr": 0.004306547156331412 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.37037037037037035, "acc_stderr": 0.04171654161354543, "acc_norm": 0.37037037037037035, "acc_norm_stderr": 0.04171654161354543 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.28289473684210525, "acc_stderr": 0.03665349695640767, "acc_norm": 0.28289473684210525, "acc_norm_stderr": 0.03665349695640767 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.41509433962264153, "acc_stderr": 0.03032594578928611, "acc_norm": 0.41509433962264153, "acc_norm_stderr": 0.03032594578928611 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3402777777777778, "acc_stderr": 0.039621355734862175, "acc_norm": 0.3402777777777778, "acc_norm_stderr": 0.039621355734862175 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.32947976878612717, "acc_stderr": 0.035839017547364106, "acc_norm": 0.32947976878612717, "acc_norm_stderr": 0.035839017547364106 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179961, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179961 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.32340425531914896, "acc_stderr": 0.030579442773610334, "acc_norm": 0.32340425531914896, "acc_norm_stderr": 0.030579442773610334 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "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": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1746031746031746, "acc_stderr": 0.03395490020856112, "acc_norm": 0.1746031746031746, "acc_norm_stderr": 0.03395490020856112 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4258064516129032, "acc_stderr": 0.0281291127091659, "acc_norm": 0.4258064516129032, "acc_norm_stderr": 0.0281291127091659 }, "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": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.44242424242424244, "acc_stderr": 0.03878372113711275, "acc_norm": 0.44242424242424244, "acc_norm_stderr": 0.03878372113711275 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.35858585858585856, "acc_stderr": 0.03416903640391521, "acc_norm": 0.35858585858585856, "acc_norm_stderr": 0.03416903640391521 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.49222797927461137, "acc_stderr": 0.036080032255696545, "acc_norm": 0.49222797927461137, "acc_norm_stderr": 0.036080032255696545 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3384615384615385, "acc_stderr": 0.02399150050031304, "acc_norm": 0.3384615384615385, "acc_norm_stderr": 0.02399150050031304 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.02684205787383371, "acc_norm": 0.26296296296296295,
