open-llm-leaderboard-old/details_defog__sqlcoder-34b-alpha
收藏数据集概述
该数据集是在对模型 defog/sqlcoder-34b-alpha 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_defog__sqlcoder-34b-alpha", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-06T03:05:19.117137 运行的最新结果：
python { "all": { "acc": 0.5437604197711231, "acc_stderr": 0.03413938521182267, "acc_norm": 0.5477802905591775, "acc_norm_stderr": 0.03485141574526089, "mc1": 0.2594859241126071, "mc1_stderr": 0.015345409485557975, "mc2": 0.40633628492072343, "mc2_stderr": 0.014173068278780471 }, "harness|arc:challenge|25": { "acc": 0.5059726962457338, "acc_stderr": 0.014610348300255793, "acc_norm": 0.5418088737201365, "acc_norm_stderr": 0.0145602203087147 }, "harness|hellaswag|10": { "acc": 0.5619398526190001, "acc_stderr": 0.004951346338164487, "acc_norm": 0.7593108942441744, "acc_norm_stderr": 0.0042662819001443916 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4740740740740741, "acc_stderr": 0.04313531696750574, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750574 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5592105263157895, "acc_stderr": 0.04040311062490435, "acc_norm": 0.5592105263157895, "acc_norm_stderr": 0.04040311062490435 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5320754716981132, "acc_stderr": 0.030709486992556545, "acc_norm": 0.5320754716981132, "acc_norm_stderr": 0.030709486992556545 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5277777777777778, "acc_stderr": 0.04174752578923185, "acc_norm": 0.5277777777777778, "acc_norm_stderr": 0.04174752578923185 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.44508670520231214, "acc_stderr": 0.03789401760283647, "acc_norm": 0.44508670520231214, "acc_norm_stderr": 0.03789401760283647 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.04755129616062947, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.04755129616062947 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.04461960433384739, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4595744680851064, "acc_stderr": 0.03257901482099835, "acc_norm": 0.4595744680851064, "acc_norm_stderr": 0.03257901482099835 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.39473684210526316, "acc_stderr": 0.045981880578165414, "acc_norm": 0.39473684210526316, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.041546596717075474, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.041546596717075474 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3968253968253968, "acc_stderr": 0.0251971010742465, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.0251971010742465 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743743, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743743 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6290322580645161, "acc_stderr": 0.027480541887953593, "acc_norm": 0.6290322580645161, "acc_norm_stderr": 0.027480541887953593 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4039408866995074, "acc_stderr": 0.0345245390382204, "acc_norm": 0.4039408866995074, "acc_norm_stderr": 0.0345245390382204 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.044084400227680794, "acc_norm": 0.74, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7090909090909091, "acc_stderr": 0.03546563019624336, "acc_norm": 0.7090909090909091, "acc_norm_stderr": 0.03546563019624336 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6818181818181818, "acc_stderr": 0.033184773338453294, "acc_norm": 0.6818181818181818, "acc_norm_stderr": 0.033184773338453294 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7772020725388601, "acc_stderr": 0.03003114797764154, "acc_norm": 0.7772020725388601, "acc_norm_stderr": 0.03003114797764154 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.49230769230769234, "acc_stderr": 0.025348006031534788, "acc_norm": 0.49230769230769234, "acc_norm_stderr": 0.025348006031534788 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948482, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.028742040903948482 }, "harness|
