open-llm-leaderboard-old/details_martyn__llama2-megamerge-dare-13b-v2
收藏数据集概述
该数据集是在评估模型 martyn/llama2-megamerge-dare-13b-v2 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
- 数据集由 63 个配置组成，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一个特定的分割，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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_martyn__llama2-megamerge-dare-13b-v2", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-18T09:10:01.856812 运行的最新结果：
python { "all": { "acc": 0.5527610511045514, "acc_stderr": 0.03393471599188749, "acc_norm": 0.5576353360299099, "acc_norm_stderr": 0.03464924134012296, "mc1": 0.32802937576499386, "mc1_stderr": 0.016435632932815025, "mc2": 0.47271389220607046, "mc2_stderr": 0.01511731653639185 }, "harness|arc:challenge|25": { "acc": 0.5563139931740614, "acc_stderr": 0.014518421825670444, "acc_norm": 0.5938566552901023, "acc_norm_stderr": 0.014351656690097858 }, "harness|hellaswag|10": { "acc": 0.6168094005178252, "acc_stderr": 0.004851705504790439, "acc_norm": 0.8093009360685123, "acc_norm_stderr": 0.003920494224883792 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "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": 0.618421052631579, "acc_stderr": 0.03953173377749194, "acc_norm": 0.618421052631579, "acc_norm_stderr": 0.03953173377749194 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.569811320754717, "acc_stderr": 0.030471445867183238, "acc_norm": 0.569811320754717, "acc_norm_stderr": 0.030471445867183238 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5763888888888888, "acc_stderr": 0.041321250197233685, "acc_norm": 0.5763888888888888, "acc_norm_stderr": 0.041321250197233685 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4508670520231214, "acc_stderr": 0.037940126746970296, "acc_norm": 0.4508670520231214, "acc_norm_stderr": 0.037940126746970296 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.04440521906179328, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.04440521906179328 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.451063829787234, "acc_stderr": 0.032529096196131965, "acc_norm": 0.451063829787234, "acc_norm_stderr": 0.032529096196131965 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2982456140350877, "acc_stderr": 0.04303684033537315, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.04303684033537315 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.47586206896551725, "acc_stderr": 0.041618085035015295, "acc_norm": 0.47586206896551725, "acc_norm_stderr": 0.041618085035015295 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.34656084656084657, "acc_stderr": 0.024508777521028424, "acc_norm": 0.34656084656084657, "acc_norm_stderr": 0.024508777521028424 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6387096774193548, "acc_stderr": 0.027327548447957543, "acc_norm": 0.6387096774193548, "acc_norm_stderr": 0.027327548447957543 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39901477832512317, "acc_stderr": 0.03445487686264716, "acc_norm": 0.39901477832512317, "acc_norm_stderr": 0.03445487686264716 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6484848484848484, "acc_stderr": 0.037282069986826503, "acc_norm": 0.6484848484848484, "acc_norm_stderr": 0.037282069986826503 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7121212121212122, "acc_stderr": 0.03225883512300992, "acc_norm": 0.7121212121212122, "acc_norm_stderr": 0.03225883512300992 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7512953367875648, "acc_stderr": 0.031195840877700286, "acc_norm": 0.7512953367875648, "acc_norm_stderr": 0.031195840877700286 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5487179487179488, "acc_stderr": 0.025230381238934833, "acc_norm": 0.5487179487179488, "acc_norm_stderr": 0.025230381238934833 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3074074074074074, "acc_stderr": 0.028133252578815642, "acc_norm": 0.
