open-llm-leaderboard-old/details_mwitiderrick__open_llama_3b_code_instruct_0.1
收藏数据集概述
数据集摘要
该数据集是在评估模型 mwitiderrick/open_llama_3b_code_instruct_0.1 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63
- 创建来源：1 次运行
- 分割命名：每个运行的分割以运行的时间戳命名，"train" 分割始终指向最新的结果。
- 额外配置："results" 配置存储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_mwitiderrick__open_llama_3b_code_instruct_0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-13T13:18:57.065820 运行的最新结果：
python { "all": { "acc": 0.28520259561896705, "acc_stderr": 0.03175383797712848, "acc_norm": 0.28706024238206684, "acc_norm_stderr": 0.03253897164366445, "mc1": 0.23133414932680538, "mc1_stderr": 0.014761945174862673, "mc2": 0.35013884322339384, "mc2_stderr": 0.013592802427042715 }, "harness|arc:challenge|25": { "acc": 0.37542662116040953, "acc_stderr": 0.014150631435111728, "acc_norm": 0.4121160409556314, "acc_norm_stderr": 0.014383915302225398 }, "harness|hellaswag|10": { "acc": 0.4938259310894244, "acc_stderr": 0.0049894009847222245, "acc_norm": 0.6695877315275841, "acc_norm_stderr": 0.004694002781939556 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.32592592592592595, "acc_stderr": 0.040491220417025055, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.040491220417025055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.29605263157894735, "acc_stderr": 0.037150621549989056, "acc_norm": 0.29605263157894735, "acc_norm_stderr": 0.037150621549989056 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.2, "acc_stderr": 0.04020151261036846, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2792452830188679, "acc_stderr": 0.02761116340239972, "acc_norm": 0.2792452830188679, "acc_norm_stderr": 0.02761116340239972 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.25, "acc_stderr": 0.03621034121889507, "acc_norm": 0.25, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.32947976878612717, "acc_stderr": 0.03583901754736411, "acc_norm": 0.32947976878612717, "acc_norm_stderr": 0.03583901754736411 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171452, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171452 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.25957446808510637, "acc_stderr": 0.028659179374292323, "acc_norm": 0.25957446808510637, "acc_norm_stderr": 0.028659179374292323 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2896551724137931, "acc_stderr": 0.03780019230438014, "acc_norm": 0.2896551724137931, "acc_norm_stderr": 0.03780019230438014 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.26455026455026454, "acc_stderr": 0.02271746789770862, "acc_norm": 0.26455026455026454, "acc_norm_stderr": 0.02271746789770862 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23015873015873015, "acc_stderr": 0.03764950879790606, "acc_norm": 0.23015873015873015, "acc_norm_stderr": 0.03764950879790606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.04688261722621503, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621503 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25161290322580643, "acc_stderr": 0.02468597928623995, "acc_norm": 0.25161290322580643, "acc_norm_stderr": 0.02468597928623995 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.0316185633535861, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.0316185633535861 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2727272727272727, "acc_stderr": 0.0347769116216366, "acc_norm": 0.2727272727272727, "acc_norm_stderr": 0.0347769116216366 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3383838383838384, "acc_stderr": 0.03371124142626301, "acc_norm": 0.3383838383838384, "acc_norm_stderr": 0.03371124142626301 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.30569948186528495, "acc_stderr": 0.033248379397581594, "acc_norm": 0.30569948186528495, "acc_norm_stderr": 0.033248379397581594 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.023901157979402538, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.023901157979402538 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.026719240783712163, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.0267192
