open-llm-leaderboard-old/details_Josephgflowers__160M-TinyLLama-Mini-Cinder
收藏数据集概述
数据集简介
该数据集是在模型Josephgflowers/160M-TinyLLama-Mini-Cinder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"分片总是指向最新的结果。
- 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_Josephgflowers__160M-TinyLLama-Mini-Cinder", "harness_winogrande_5", split="train")
最新结果
以下是最新结果来自2024-02-09T17:13:35.255833：
python { "all": { "acc": 0.25091674200376424, "acc_stderr": 0.03066057799931663, "acc_norm": 0.25135766305613044, "acc_norm_stderr": 0.031476579516341745, "mc1": 0.2631578947368421, "mc1_stderr": 0.015415241740237014, "mc2": 0.44082567345001694, "mc2_stderr": 0.01569726938506295 }, "harness|arc:challenge|25": { "acc": 0.20392491467576793, "acc_stderr": 0.01177426247870225, "acc_norm": 0.24658703071672355, "acc_norm_stderr": 0.01259572626879013 }, "harness|hellaswag|10": { "acc": 0.2744473212507469, "acc_stderr": 0.004453233726110324, "acc_norm": 0.28161720772754434, "acc_norm_stderr": 0.004488684397979513 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.26666666666666666, "acc_stderr": 0.038201699145179055, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.038201699145179055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.20394736842105263, "acc_stderr": 0.032790004063100515, "acc_norm": 0.20394736842105263, "acc_norm_stderr": 0.032790004063100515 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.20754716981132076, "acc_stderr": 0.024959918028911274, "acc_norm": 0.20754716981132076, "acc_norm_stderr": 0.024959918028911274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2152777777777778, "acc_stderr": 0.03437079344106135, "acc_norm": 0.2152777777777778, "acc_norm_stderr": 0.03437079344106135 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036844, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036844 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749895, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749895 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364395, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364395 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748141, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748141 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.23448275862068965, "acc_stderr": 0.035306258743465914, "acc_norm": 0.23448275862068965, "acc_norm_stderr": 0.035306258743465914 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.21957671957671956, "acc_stderr": 0.02132001859977035, "acc_norm": 0.21957671957671956, "acc_norm_stderr": 0.02132001859977035 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.03932537680392872, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.03932537680392872 }, "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": 0.2870967741935484, "acc_stderr": 0.025736542745594525, "acc_norm": 0.2870967741935484, "acc_norm_stderr": 0.025736542745594525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.30049261083743845, "acc_stderr": 0.03225799476233483, "acc_norm": 0.30049261083743845, "acc_norm_stderr": 0.03225799476233483 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.28484848484848485, "acc_stderr": 0.035243908445117836, "acc_norm": 0.28484848484848485, "acc_norm_stderr": 0.035243908445117836 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2828282828282828, "acc_stderr": 0.03208779558786751, "acc_norm": 0.2828282828282828, "acc_norm_stderr": 0.03208779558786751 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.25906735751295334, "acc_stderr": 0.03161877917935409, "acc_norm": 0.25906735751295334, "acc_norm_stderr": 0.03161877917935409 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2153846153846154, "acc_stderr": 0.020843034557462878, "acc_norm": 0.2153846153846154, "acc_norm_stderr": 0.020843034557462878 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.026842057
