open-llm-leaderboard-old/details_ZhangShenao__0.0_ablation_sample1_4iters_bs256_iter_4
收藏数据集概述
该数据集是在对模型 ZhangShenao/0.0_ablation_sample1_4iters_bs256_iter_4 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 该数据集包含 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_ZhangShenao__0.0_ablation_sample1_4iters_bs256_iter_4", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-24T11:24:28.890855 运行的最新结果：
python { "all": { "acc": 0.5973228120038028, "acc_stderr": 0.03311682310077929, "acc_norm": 0.6058987465075552, "acc_norm_stderr": 0.033866210672608726, "mc1": 0.3733170134638923, "mc1_stderr": 0.01693237055757063, "mc2": 0.5416848979620421, "mc2_stderr": 0.016332240010603016 }, "harness|arc:challenge|25": { "acc": 0.5853242320819113, "acc_stderr": 0.014397070564409174, "acc_norm": 0.6075085324232082, "acc_norm_stderr": 0.014269634635670726 }, "harness|hellaswag|10": { "acc": 0.6659032065325632, "acc_stderr": 0.004707097816047557, "acc_norm": 0.8506273650667198, "acc_norm_stderr": 0.00355726903934218 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5481481481481482, "acc_stderr": 0.042992689054808644, "acc_norm": 0.5481481481481482, "acc_norm_stderr": 0.042992689054808644 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.03910525752849724, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.03910525752849724 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6754716981132075, "acc_stderr": 0.02881561571343211, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.02881561571343211 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.03703851193099521, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768079, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5319148936170213, "acc_stderr": 0.03261936918467383, "acc_norm": 0.5319148936170213, "acc_norm_stderr": 0.03261936918467383 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.04164188720169377, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.04164188720169377 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42857142857142855, "acc_stderr": 0.02548718714785938, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.02548718714785938 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7225806451612903, "acc_stderr": 0.025470196835900055, "acc_norm": 0.7225806451612903, "acc_norm_stderr": 0.025470196835900055 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4876847290640394, "acc_stderr": 0.035169204442208966, "acc_norm": 0.4876847290640394, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7373737373737373, "acc_stderr": 0.031353050095330855, "acc_norm": 0.7373737373737373, "acc_norm_stderr": 0.031353050095330855 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.026499057701397457, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.026499057701397457 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5666666666666667, "acc_stderr": 0.025124653525885117, "acc_norm": 0.5666666666666667, "acc_norm_stderr": 0.025124653525885117 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.028037929969114986, "acc_norm": 0.3
