open-llm-leaderboard-old/details_netcat420__MFANN3bv0.3
收藏数据集概述
该数据集是在评估模型 netcat420/MFANN3bv0.3 在 Open LLM Leaderboard 上的运行过程中自动创建的。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
- 配置数量：63
- 数据来源：1 次运行
- 数据分割：每个配置包含特定运行的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置："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_netcat420__MFANN3bv0.3", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-10T11:05:44.382193 运行的最新结果：
python { "all": { "acc": 0.5640181636429435, "acc_stderr": 0.03395709961520436, "acc_norm": 0.5644577599251721, "acc_norm_stderr": 0.03466061021433457, "mc1": 0.36474908200734396, "mc1_stderr": 0.01685096106172012, "mc2": 0.5310482277801756, "mc2_stderr": 0.01563364334134236 }, "harness|arc:challenge|25": { "acc": 0.6040955631399317, "acc_stderr": 0.014291228393536587, "acc_norm": 0.6168941979522184, "acc_norm_stderr": 0.014206472661672876 }, "harness|hellaswag|10": { "acc": 0.5737900816570405, "acc_stderr": 0.004935143791573814, "acc_norm": 0.7673770165305716, "acc_norm_stderr": 0.004216404041910502 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.43703703703703706, "acc_stderr": 0.04284958639753399, "acc_norm": 0.43703703703703706, "acc_norm_stderr": 0.04284958639753399 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5328947368421053, "acc_stderr": 0.040601270352363966, "acc_norm": 0.5328947368421053, "acc_norm_stderr": 0.040601270352363966 }, "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": 0.5849056603773585, "acc_stderr": 0.03032594578928611, "acc_norm": 0.5849056603773585, "acc_norm_stderr": 0.03032594578928611 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325582, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325582 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5953757225433526, "acc_stderr": 0.03742461193887249, "acc_norm": 0.5953757225433526, "acc_norm_stderr": 0.03742461193887249 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105654, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4595744680851064, "acc_stderr": 0.03257901482099834, "acc_norm": 0.4595744680851064, "acc_norm_stderr": 0.03257901482099834 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.04462917535336936, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.04462917535336936 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.47586206896551725, "acc_stderr": 0.041618085035015295, "acc_norm": 0.47586206896551725, "acc_norm_stderr": 0.041618085035015295 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4365079365079365, "acc_stderr": 0.025542846817400496, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.025542846817400496 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.044444444444444495, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.044444444444444495 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7193548387096774, "acc_stderr": 0.025560604721022895, "acc_norm": 0.7193548387096774, "acc_norm_stderr": 0.025560604721022895 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.45320197044334976, "acc_stderr": 0.03502544650845872, "acc_norm": 0.45320197044334976, "acc_norm_stderr": 0.03502544650845872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6606060606060606, "acc_stderr": 0.03697442205031596, "acc_norm": 0.6606060606060606, "acc_norm_stderr": 0.03697442205031596 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7323232323232324, "acc_stderr": 0.03154449888270285, "acc_norm": 0.7323232323232324, "acc_norm_stderr": 0.03154449888270285 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.772020725388601, "acc_stderr": 0.030276909945178263, "acc_norm": 0.772020725388601, "acc_norm_stderr": 0.030276909945178263 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5923076923076923, "acc_stderr": 0.024915243985987847, "acc_norm": 0.5923076923076923, "acc_norm_stderr": 0.024915243985987847 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.36666666666666664, "acc_stderr": 0.029381620726465073, "acc_norm": 0.36666666666666
