open-llm-leaderboard-old/details_Delcos__Starling-LM-11B-alpha
收藏数据集概述
数据集创建背景
该数据集是在对模型 Delcos/Starling-LM-11B-alpha 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的特定分片形式存储。"train" 分片始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 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_Delcos__Starling-LM-11B-alpha", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-09T16:46:23.982029 运行的最新结果：
python { "all": { "acc": 0.6362170386987497, "acc_stderr": 0.03232328033089801, "acc_norm": 0.6416906108621553, "acc_norm_stderr": 0.03297213400326341, "mc1": 0.38922888616891066, "mc1_stderr": 0.01706855268069033, "mc2": 0.5452023492477854, "mc2_stderr": 0.016056772234309992 }, "harness|arc:challenge|25": { "acc": 0.6006825938566553, "acc_stderr": 0.014312094557946705, "acc_norm": 0.6296928327645052, "acc_norm_stderr": 0.01411129875167495 }, "harness|hellaswag|10": { "acc": 0.668990240987851, "acc_stderr": 0.004696148339570979, "acc_norm": 0.8485361481776539, "acc_norm_stderr": 0.0035776774950640783 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.042320736951515885, "acc_norm": 0.6, "acc_norm_stderr": 0.042320736951515885 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.03738520676119669, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.03738520676119669 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6566037735849056, "acc_stderr": 0.02922452646912479, "acc_norm": 0.6566037735849056, "acc_norm_stderr": 0.02922452646912479 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7430555555555556, "acc_stderr": 0.03653946969442099, "acc_norm": 0.7430555555555556, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6994219653179191, "acc_stderr": 0.03496101481191179, "acc_norm": 0.6994219653179191, "acc_norm_stderr": 0.03496101481191179 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.45098039215686275, "acc_stderr": 0.049512182523962625, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.049512182523962625 }, "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": 0.5702127659574469, "acc_stderr": 0.03236214467715564, "acc_norm": 0.5702127659574469, "acc_norm_stderr": 0.03236214467715564 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5172413793103449, "acc_stderr": 0.04164188720169375, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.04164188720169375 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.025305906241590632, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.025305906241590632 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5238095238095238, "acc_stderr": 0.04467062628403273, "acc_norm": 0.5238095238095238, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7548387096774194, "acc_stderr": 0.024472243840895535, "acc_norm": 0.7548387096774194, "acc_norm_stderr": 0.024472243840895535 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.458128078817734, "acc_stderr": 0.03505630140785741, "acc_norm": 0.458128078817734, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.03192271569548301, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.03192271569548301 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8080808080808081, "acc_stderr": 0.02805779167298902, "acc_norm": 0.8080808080808081, "acc_norm_stderr": 0.02805779167298902 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8911917098445595, "acc_stderr": 0.02247325333276878, "acc_norm": 0.8911917098445595, "acc_norm_stderr": 0.02247325333276878 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6410256410256411, "acc_stderr": 0.024321738484602354, "acc_norm": 0.6410256410256411, "acc_norm_stderr": 0.024321738484602354 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.028037929969114986, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.028037929969114986
