open-llm-leaderboard/details_TheBloke__Wizard-Vicuna-30B-Superhot-8K-fp16
收藏数据集概述
数据集摘要
该数据集是在对模型 TheBloke/Wizard-Vicuna-30B-Superhot-8K-fp16 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 61 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找到特定的分割，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。
加载数据集示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_TheBloke__Wizard-Vicuna-30B-Superhot-8K-fp16", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-07-31T18:46:06.024423 运行的最新结果：
python { "all": { "acc": 0.23519468841762173, "acc_stderr": 0.030867946729594396, "acc_norm": 0.23665032922383497, "acc_norm_stderr": 0.03088234450623421, "mc1": 0.22766217870257038, "mc1_stderr": 0.01467925503211107, "mc2": 0.4747511496520905, "mc2_stderr": 0.016743067237896876 }, "harness|arc:challenge|25": { "acc": 0.22525597269624573, "acc_stderr": 0.012207839995407312, "acc_norm": 0.2619453924914676, "acc_norm_stderr": 0.012849054826858115 }, "harness|hellaswag|10": { "acc": 0.2804222266480781, "acc_stderr": 0.004482874732237348, "acc_norm": 0.3296156144194384, "acc_norm_stderr": 0.004691128722535483 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.1925925925925926, "acc_stderr": 0.03406542058502653, "acc_norm": 0.1925925925925926, "acc_norm_stderr": 0.03406542058502653 }, "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": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.19245283018867926, "acc_stderr": 0.024262979839372277, "acc_norm": 0.19245283018867926, "acc_norm_stderr": 0.024262979839372277 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749874, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749874 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135303, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135303 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24867724867724866, "acc_stderr": 0.022261817692400168, "acc_norm": 0.24867724867724866, "acc_norm_stderr": 0.022261817692400168 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.04040610178208841, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.04040610178208841 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.18064516129032257, "acc_stderr": 0.02188617856717255, "acc_norm": 0.18064516129032257, "acc_norm_stderr": 0.02188617856717255 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.15270935960591134, "acc_stderr": 0.02530890453938063, "acc_norm": 0.15270935960591134, "acc_norm_stderr": 0.02530890453938063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2606060606060606, "acc_stderr": 0.03427743175816524, "acc_norm": 0.2606060606060606, "acc_norm_stderr": 0.03427743175816524 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.17676767676767677, "acc_stderr": 0.027178752639044915, "acc_norm": 0.17676767676767677, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.18652849740932642, "acc_stderr": 0.028112091210117447, "acc_norm": 0.18652849740932642, "acc_norm_stderr": 0.028112091210117447 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2128205128205128, "acc_stderr": 0.020752423722127995, "acc_norm": 0.2128205128205128, "acc_norm_stderr": 0.020752423722127995 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2481481481
