open-llm-leaderboard-old/details_vilm__Mixsmol-4x400M-v0.1-epoch1
收藏数据集概述
数据集名称
Evaluation run of vilm/Mixsmol-4x400M-v0.1-epoch1
数据集摘要
该数据集是在模型 vilm/Mixsmol-4x400M-v0.1-epoch1 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割找到，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
- 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 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_vilm__Mixsmol-4x400M-v0.1-epoch1", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-01-29T06:43:16.109579 的运行： python { "all": { "acc": 0.2528141388237338, "acc_stderr": 0.03070376097869733, "acc_norm": 0.2532398880953499, "acc_norm_stderr": 0.03150013405049895, "mc1": 0.20685434516523868, "mc1_stderr": 0.014179591496728343, "mc2": 0.39031505296680813, "mc2_stderr": 0.014793512649281262 }, "harness|arc:challenge|25": { "acc": 0.19965870307167236, "acc_stderr": 0.01168162575688867, "acc_norm": 0.22866894197952217, "acc_norm_stderr": 0.012272853582540802 }, "harness|hellaswag|10": { "acc": 0.285700059749054, "acc_stderr": 0.004508239594503833, "acc_norm": 0.3057159928301135, "acc_norm_stderr": 0.004597684609707824 }, "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": 0.22962962962962963, "acc_stderr": 0.03633384414073465, "acc_norm": 0.22962962962962963, "acc_norm_stderr": 0.03633384414073465 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21509433962264152, "acc_stderr": 0.025288394502891366, "acc_norm": 0.21509433962264152, "acc_norm_stderr": 0.025288394502891366 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.24305555555555555, "acc_stderr": 0.03586879280080341, "acc_norm": 0.24305555555555555, "acc_norm_stderr": 0.03586879280080341 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "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": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2774566473988439, "acc_stderr": 0.03414014007044036, "acc_norm": 0.2774566473988439, "acc_norm_stderr": 0.03414014007044036 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.04336432707993179, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.04336432707993179 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2851063829787234, "acc_stderr": 0.029513196625539355, "acc_norm": 0.2851063829787234, "acc_norm_stderr": 0.029513196625539355 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21929824561403508, "acc_stderr": 0.03892431106518754, "acc_norm": 0.21929824561403508, "acc_norm_stderr": 0.03892431106518754 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.25517241379310346, "acc_stderr": 0.03632984052707841, "acc_norm": 0.25517241379310346, "acc_norm_stderr": 0.03632984052707841 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.022418042891113942, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.022418042891113942 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15873015873015872, "acc_stderr": 0.03268454013011743, "acc_norm": 0.15873015873015872, "acc_norm_stderr": 0.03268454013011743 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.19, "acc_stderr": 0.03942772444036624, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3032258064516129, "acc_stderr": 0.02614868593067175, "acc_norm": 0.3032258064516129, "acc_norm_stderr": 0.02614868593067175 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.29064039408866993, "acc_stderr": 0.0319474007226554, "acc_norm": 0.29064039408866993, "acc_norm_stderr": 0.0319474007226554 }, "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": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25252525252525254, "acc_stderr": 0.030954055470365897, "acc_norm": 0.25252525252525254, "acc_norm_stderr": 0.030954055470365897 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.35751295336787564, "acc_stderr": 0.034588160421810045, "acc_norm": 0.35751295336787564, "acc_norm_stderr": 0.034588160421810045 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2358974358974359, "acc_stderr": 0.021525965407408726, "acc_norm": 0.2358974358974359, "acc_norm_stderr": 0.021525965407408726 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.026842057873833706, "acc_norm": 0.26296296296296295
