open-llm-leaderboard-old/details_jan-ai__Solar-10.7B-SLERP
收藏数据集概述
数据集摘要
该数据集是在对模型 jan-ai/Solar-10.7B-SLERP 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。
- 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_jan-ai__Solar-10.7B-SLERP", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-16T15:35:26.592676 运行的最新结果：
python { "all": { "acc": 0.6608479464480653, "acc_stderr": 0.031968087444665505, "acc_norm": 0.6623335219673708, "acc_norm_stderr": 0.03261535081063273, "mc1": 0.5079559363525091, "mc1_stderr": 0.01750128507455183, "mc2": 0.6571842191607326, "mc2_stderr": 0.015609617120580309 }, "harness|arc:challenge|25": { "acc": 0.6791808873720137, "acc_stderr": 0.013640943091946528, "acc_norm": 0.7073378839590444, "acc_norm_stderr": 0.013295916103619422 }, "harness|hellaswag|10": { "acc": 0.7035451105357499, "acc_stderr": 0.004557606227194303, "acc_norm": 0.8787094204341764, "acc_norm_stderr": 0.003257974593789937 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.04171654161354543, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.04171654161354543 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "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": 0.7169811320754716, "acc_stderr": 0.027724236492700918, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700918 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.75, "acc_stderr": 0.03621034121889507, "acc_norm": 0.75, "acc_norm_stderr": 0.03621034121889507 }, "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": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6242774566473989, "acc_stderr": 0.036928207672648664, "acc_norm": 0.6242774566473989, "acc_norm_stderr": 0.036928207672648664 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816507, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5914893617021276, "acc_stderr": 0.032134180267015755, "acc_norm": 0.5914893617021276, "acc_norm_stderr": 0.032134180267015755 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5263157894736842, "acc_stderr": 0.046970851366478626, "acc_norm": 0.5263157894736842, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878152, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878152 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4894179894179894, "acc_stderr": 0.02574554227604548, "acc_norm": 0.4894179894179894, "acc_norm_stderr": 0.02574554227604548 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "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": 0.7935483870967742, "acc_stderr": 0.023025899617188712, "acc_norm": 0.7935483870967742, "acc_norm_stderr": 0.023025899617188712 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "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": 0.8242424242424242, "acc_stderr": 0.02972094300622445, "acc_norm": 0.8242424242424242, "acc_norm_stderr": 0.02972094300622445 }, "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": 0.9015544041450777, "acc_stderr": 0.02150024957603344, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.02150024957603344 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6564102564102564, "acc_stderr": 0.024078696580635477, "acc_norm": 0.6564102564102564, "acc_norm_stderr": 0.024078696580635477 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251976, "acc_norm": 0.3592592592592593, "acc_norm_stderr": 0.029252905927251976 }, "harness|hendrycksTest-high_school_
