open-llm-leaderboard-old/details_tlphams__zoyllm-7b-slimorca
收藏数据集概述
数据集摘要
该数据集是在对模型 tlphams/zoyllm-7b-slimorca 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_tlphams__zoyllm-7b-slimorca", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-04T20:19:06.813924 运行的最新结果：
python { "all": { "acc": 0.4870010988384523, "acc_stderr": 0.03455949361884823, "acc_norm": 0.4920391497879656, "acc_norm_stderr": 0.03531050289249056, "mc1": 0.32313341493268055, "mc1_stderr": 0.016371836286454604, "mc2": 0.4913166366572656, "mc2_stderr": 0.0160517163595852 }, "harness|arc:challenge|25": { "acc": 0.4726962457337884, "acc_stderr": 0.014589589101985993, "acc_norm": 0.5059726962457338, "acc_norm_stderr": 0.014610348300255795 }, "harness|hellaswag|10": { "acc": 0.5509858593905597, "acc_stderr": 0.004963771168672079, "acc_norm": 0.7211710814578769, "acc_norm_stderr": 0.004475067344626756 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04292596718256981, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04292596718256981 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.45394736842105265, "acc_stderr": 0.04051646342874142, "acc_norm": 0.45394736842105265, "acc_norm_stderr": 0.04051646342874142 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5358490566037736, "acc_stderr": 0.030693675018458, "acc_norm": 0.5358490566037736, "acc_norm_stderr": 0.030693675018458 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4722222222222222, "acc_stderr": 0.04174752578923185, "acc_norm": 0.4722222222222222, "acc_norm_stderr": 0.04174752578923185 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4393063583815029, "acc_stderr": 0.037842719328874674, "acc_norm": 0.4393063583815029, "acc_norm_stderr": 0.037842719328874674 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.29411764705882354, "acc_stderr": 0.04533838195929776, "acc_norm": 0.29411764705882354, "acc_norm_stderr": 0.04533838195929776 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4127659574468085, "acc_stderr": 0.03218471141400351, "acc_norm": 0.4127659574468085, "acc_norm_stderr": 0.03218471141400351 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2543859649122807, "acc_stderr": 0.04096985139843672, "acc_norm": 0.2543859649122807, "acc_norm_stderr": 0.04096985139843672 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.37566137566137564, "acc_stderr": 0.024942368931159788, "acc_norm": 0.37566137566137564, "acc_norm_stderr": 0.024942368931159788 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3412698412698413, "acc_stderr": 0.04240799327574924, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.04240799327574924 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5741935483870968, "acc_stderr": 0.028129112709165904, "acc_norm": 0.5741935483870968, "acc_norm_stderr": 0.028129112709165904 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.33004926108374383, "acc_stderr": 0.03308530426228257, "acc_norm": 0.33004926108374383, "acc_norm_stderr": 0.03308530426228257 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6545454545454545, "acc_stderr": 0.037131580674819135, "acc_norm": 0.6545454545454545, "acc_norm_stderr": 0.037131580674819135 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6414141414141414, "acc_stderr": 0.034169036403915214, "acc_norm": 0.6414141414141414, "acc_norm_stderr": 0.034169036403915214 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6528497409326425, "acc_stderr": 0.03435696168361356, "acc_norm": 0.6528497409326425, "acc_norm_stderr": 0.03435696168361356 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4230769230769231, "acc_stderr": 0.025049197876042338, "acc_norm": 0.4230769230769231, "acc_norm_stderr": 0.025049197876042338 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.02696242432507382, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.02696242432507382
