open-llm-leaderboard-old/details_leejaymin__etri-ones-solar
收藏数据集概述
该数据集是在对模型 leejaymin/etri-ones-solar 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。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
数据集由以下部分组成：
- 63 个配置：每个配置对应一个评估任务。
- 1 次运行：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：始终指向最新的结果。
- "results" 配置：存储所有运行的聚合结果，用于计算和显示聚合指标。
数据加载示例
以下是加载数据集的示例代码：
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_leejaymin__etri-ones-solar", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要：
python { "all": { "acc": 0.6289828180315297, "acc_stderr": 0.03199524578851419, "acc_norm": 0.6403658725397634, "acc_norm_stderr": 0.03287306734304755, "mc1": 0.36474908200734396, "mc1_stderr": 0.016850961061720113, "mc2": 0.5269096033669528, "mc2_stderr": 0.014940096900050902 }, "harness|arc:challenge|25": { "acc": 0.5861774744027304, "acc_stderr": 0.014392730009221007, "acc_norm": 0.6262798634812287, "acc_norm_stderr": 0.014137708601759091 }, "harness|hellaswag|10": { "acc": 0.6502688707428799, "acc_stderr": 0.004759103432380765, "acc_norm": 0.8430591515634336, "acc_norm_stderr": 0.0036300159898964056 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7368421052631579, "acc_stderr": 0.035834961763610736, "acc_norm": 0.7368421052631579, "acc_norm_stderr": 0.035834961763610736 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.73, "acc_stderr": 0.044619604333847415, "acc_norm": 0.73, "acc_norm_stderr": 0.044619604333847415 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6641509433962264, "acc_stderr": 0.029067220146644833, "acc_norm": 0.6641509433962264, "acc_norm_stderr": 0.029067220146644833 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7569444444444444, "acc_stderr": 0.0358687928008034, "acc_norm": 0.7569444444444444, "acc_norm_stderr": 0.0358687928008034 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.036430371689585475, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.036430371689585475 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.048971049527263666, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.548936170212766, "acc_stderr": 0.032529096196131965, "acc_norm": 0.548936170212766, "acc_norm_stderr": 0.032529096196131965 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.42105263157894735, "acc_stderr": 0.046446020912223177, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4576719576719577, "acc_stderr": 0.025658868862058336, "acc_norm": 0.4576719576719577, "acc_norm_stderr": 0.025658868862058336 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3968253968253968, "acc_stderr": 0.04375888492727061, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.04375888492727061 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7451612903225806, "acc_stderr": 0.02479011845933221, "acc_norm": 0.7451612903225806, "acc_norm_stderr": 0.02479011845933221 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.46798029556650245, "acc_stderr": 0.035107665979592154, "acc_norm": 0.46798029556650245, "acc_norm_stderr": 0.035107665979592154 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8282828282828283, "acc_stderr": 0.026869716187429903, "acc_norm": 0.8282828282828283, "acc_norm_stderr": 0.026869716187429903 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.023381935348121437, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.023381935348121437 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6076923076923076, "acc_stderr": 0.02475600038213095, "acc_norm": 0.6076923076923076, "acc_norm_stderr": 0.02475600038213095 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4, "acc_stderr": 0.02986960509531691, "acc_norm": 0.4, "acc_norm_stderr": 0.02986960509531691 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6554621848739496, "acc_stderr": 0.030868682604121626, "acc_norm": 0.655462
