open-llm-leaderboard-old/details_robinsmits__Qwen1.5-7B-Dutch-Chat-Sft
收藏数据集概述
数据集简介
该数据集是在评估模型 robinsmits/Qwen1.5-7B-Dutch-Chat-Sft 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。
- 数据集由 1 次运行创建，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_robinsmits__Qwen1.5-7B-Dutch-Chat-Sft", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-29T20:04:27.887464 运行的最新结果：
python { "all": { "acc": 0.5978454719542368, "acc_stderr": 0.03318702690067964, "acc_norm": 0.6052027087641982, "acc_norm_stderr": 0.03386918430024484, "mc1": 0.2839657282741738, "mc1_stderr": 0.01578537085839673, "mc2": 0.4389025272424357, "mc2_stderr": 0.014718286096688073 }, "harness|arc:challenge|25": { "acc": 0.4803754266211604, "acc_stderr": 0.014600132075947087, "acc_norm": 0.5068259385665529, "acc_norm_stderr": 0.014610029151379812 }, "harness|hellaswag|10": { "acc": 0.5421230830511851, "acc_stderr": 0.004972042602001382, "acc_norm": 0.7349133638717387, "acc_norm_stderr": 0.004404772735765973 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6776315789473685, "acc_stderr": 0.03803510248351585, "acc_norm": 0.6776315789473685, "acc_norm_stderr": 0.03803510248351585 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "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": 0.6944444444444444, "acc_stderr": 0.03852084696008534, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.03852084696008534 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.05021167315686779, "acc_norm": 0.48, "acc_norm_stderr": 0.05021167315686779 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5780346820809249, "acc_stderr": 0.037657466938651504, "acc_norm": 0.5780346820809249, "acc_norm_stderr": 0.037657466938651504 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5234042553191489, "acc_stderr": 0.03265019475033582, "acc_norm": 0.5234042553191489, "acc_norm_stderr": 0.03265019475033582 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.04657047260594962, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.04657047260594962 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6068965517241379, "acc_stderr": 0.040703290137070705, "acc_norm": 0.6068965517241379, "acc_norm_stderr": 0.040703290137070705 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47354497354497355, "acc_stderr": 0.025715239811346755, "acc_norm": 0.47354497354497355, "acc_norm_stderr": 0.025715239811346755 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768176, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768176 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7096774193548387, "acc_stderr": 0.025822106119415888, "acc_norm": 0.7096774193548387, "acc_norm_stderr": 0.025822106119415888 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.541871921182266, "acc_stderr": 0.03505630140785742, "acc_norm": 0.541871921182266, "acc_norm_stderr": 0.03505630140785742 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "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": 0.8031088082901554, "acc_stderr": 0.028697873971860667, "acc_norm": 0.8031088082901554, "acc_norm_stderr": 0.028697873971860667 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5871794871794872, "acc_stderr": 0.024962683564331796, "acc_norm": 0.5871794871794872, "acc_norm_stderr": 0.024962683564331796 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3111111111111111, "acc_stderr": 0.02822644674968352, "acc_norm": 0.31111111111
