open-llm-leaderboard-old/details_uukuguy__airoboros-m-7b-3.1.2-dare-0.85
收藏数据集概述
数据集名称
Evaluation run of uukuguy/airoboros-m-7b-3.1.2-dare-0.85
数据集摘要
该数据集是在模型 uukuguy/airoboros-m-7b-3.1.2-dare-0.85 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 64 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片找到，分片名称使用运行的时间戳。"train" 分片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，用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_uukuguy__airoboros-m-7b-3.1.2-dare-0.85_public", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2023-11-23T23:04:08.316762 的运行： python { "all": { "acc": 0.634042190068382, "acc_stderr": 0.032283010718078695, "acc_norm": 0.6433235552057146, "acc_norm_stderr": 0.03298195134123534, "mc1": 0.2937576499388005, "mc1_stderr": 0.015945068581236614, "mc2": 0.43638896018594414, "mc2_stderr": 0.01419131146424957, "em": 0.0016778523489932886, "em_stderr": 0.00041913301788268467, "f1": 0.06136954697986581, "f1_stderr": 0.0013699074965009578 }, "harness|arc:challenge|25": { "acc": 0.575938566552901, "acc_stderr": 0.0144418896274644, "acc_norm": 0.6109215017064846, "acc_norm_stderr": 0.014247309976045607 }, "harness|hellaswag|10": { "acc": 0.6330412268472416, "acc_stderr": 0.00480990115123484, "acc_norm": 0.8356901015733917, "acc_norm_stderr": 0.003697992356124477 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595852, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595852 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.03842498559395268, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.03842498559395268 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6830188679245283, "acc_stderr": 0.02863723563980089, "acc_norm": 0.6830188679245283, "acc_norm_stderr": 0.02863723563980089 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.03716177437566017, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.03716177437566017 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.04897104952726366, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.04897104952726366 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036845, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5702127659574469, "acc_stderr": 0.03236214467715564, "acc_norm": 0.5702127659574469, "acc_norm_stderr": 0.03236214467715564 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555497, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555497 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3862433862433862, "acc_stderr": 0.02507598176760168, "acc_norm": 0.3862433862433862, "acc_norm_stderr": 0.02507598176760168 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.0436031486007746, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.0436031486007746 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7677419354838709, "acc_stderr": 0.024022256130308235, "acc_norm": 0.7677419354838709, "acc_norm_stderr": 0.024022256130308235 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5221674876847291, "acc_stderr": 0.03514528562175008, "acc_norm": 0.5221674876847291, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621504, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7636363636363637, "acc_stderr": 0.03317505930009182, "acc_norm": 0.7636363636363637, "acc_norm_stderr": 0.03317505930009182 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7626262626262627, "acc_stderr": 0.0303137105381989, "acc_norm": 0.7626262626262627, "acc_norm_stderr": 0.0303137105381989 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.02381447708659355, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.02381447708659355 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.658974358974359, "acc_stderr": 0.02403548967633508, "acc_norm": 0.658974358974359, "acc_norm_stderr": 0.02403548967633508 }, "harness
