open-llm-leaderboard-old/details_frankenmerger__delta-4B-super
收藏数据集概述
该数据集是在对模型 frankenmerger/delta-4B-super 进行评估运行期间自动创建的，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，每次运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。
- "train" 拆分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_frankenmerger__delta-4B-super", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-10T11:33:31.513769 运行的最新结果：
python { "all": { "acc": 0.5905528687838363, "acc_stderr": 0.03352325174942067, "acc_norm": 0.5934267748828804, "acc_norm_stderr": 0.034203989694081526, "mc1": 0.3684210526315789, "mc1_stderr": 0.016886551261046042, "mc2": 0.5173591737183307, "mc2_stderr": 0.016143767707448048 }, "harness|arc:challenge|25": { "acc": 0.5674061433447098, "acc_stderr": 0.014478005694182526, "acc_norm": 0.5861774744027304, "acc_norm_stderr": 0.014392730009221004 }, "harness|hellaswag|10": { "acc": 0.5875323640709023, "acc_stderr": 0.0049127238489447955, "acc_norm": 0.7628958374825732, "acc_norm_stderr": 0.004244374809273614 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5185185185185185, "acc_stderr": 0.043163785995113245, "acc_norm": 0.5185185185185185, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.618421052631579, "acc_stderr": 0.03953173377749194, "acc_norm": 0.618421052631579, "acc_norm_stderr": 0.03953173377749194 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.66, "acc_stderr": 0.04760952285695238, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695238 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6264150943396226, "acc_stderr": 0.02977308271331987, "acc_norm": 0.6264150943396226, "acc_norm_stderr": 0.02977308271331987 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6458333333333334, "acc_stderr": 0.039994111357535424, "acc_norm": 0.6458333333333334, "acc_norm_stderr": 0.039994111357535424 }, "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": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6127167630057804, "acc_stderr": 0.03714325906302065, "acc_norm": 0.6127167630057804, "acc_norm_stderr": 0.03714325906302065 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.048580835742663434, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.048580835742663434 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.046882617226215034, "acc_norm": 0.68, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5063829787234042, "acc_stderr": 0.032683358999363366, "acc_norm": 0.5063829787234042, "acc_norm_stderr": 0.032683358999363366 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.35964912280701755, "acc_stderr": 0.045144961328736334, "acc_norm": 0.35964912280701755, "acc_norm_stderr": 0.045144961328736334 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4470899470899471, "acc_stderr": 0.025606723995777025, "acc_norm": 0.4470899470899471, "acc_norm_stderr": 0.025606723995777025 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7096774193548387, "acc_stderr": 0.025822106119415895, "acc_norm": 0.7096774193548387, "acc_norm_stderr": 0.025822106119415895 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4630541871921182, "acc_stderr": 0.035083705204426656, "acc_norm": 0.4630541871921182, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6848484848484848, "acc_stderr": 0.0362773057502241, "acc_norm": 0.6848484848484848, "acc_norm_stderr": 0.0362773057502241 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.02985751567338642, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.02985751567338642 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758733, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758733 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6307692307692307, "acc_stderr": 0.024468615241478926, "acc_norm": 0.6307692307692307, "acc_norm_stderr": 0.024468615241478926 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.0287420409039485, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.02
