open-llm-leaderboard-old/details_mncai__yi-34B-v3
收藏数据集概述
数据集描述
该数据集是在对模型 mncai/yi-34B-v3 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。
额外配置
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_mncai__yi-34B-v3", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-11T01:51:08.694143 运行的最新结果：
python { "all": { "acc": 0.7536948044621744, "acc_stderr": 0.028378789321173548, "acc_norm": 0.7581198984934292, "acc_norm_stderr": 0.02891498378900509, "mc1": 0.4186046511627907, "mc1_stderr": 0.017270015284476855, "mc2": 0.5753679426280454, "mc2_stderr": 0.014962842073717312 }, "harness|arc:challenge|25": { "acc": 0.6390784982935154, "acc_stderr": 0.014034761386175452, "acc_norm": 0.6706484641638225, "acc_norm_stderr": 0.013734057652635476 }, "harness|hellaswag|10": { "acc": 0.6487751443935471, "acc_stderr": 0.004763774981834676, "acc_norm": 0.8511252738498307, "acc_norm_stderr": 0.0035523745313052004 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6962962962962963, "acc_stderr": 0.03972552884785137, "acc_norm": 0.6962962962962963, "acc_norm_stderr": 0.03972552884785137 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.881578947368421, "acc_stderr": 0.026293995855474935, "acc_norm": 0.881578947368421, "acc_norm_stderr": 0.026293995855474935 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8188679245283019, "acc_stderr": 0.023702963526757798, "acc_norm": 0.8188679245283019, "acc_norm_stderr": 0.023702963526757798 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9097222222222222, "acc_stderr": 0.023964965777906935, "acc_norm": 0.9097222222222222, "acc_norm_stderr": 0.023964965777906935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7167630057803468, "acc_stderr": 0.034355680560478746, "acc_norm": 0.7167630057803468, "acc_norm_stderr": 0.034355680560478746 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5392156862745098, "acc_stderr": 0.04959859966384181, "acc_norm": 0.5392156862745098, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7787234042553192, "acc_stderr": 0.027136349602424056, "acc_norm": 0.7787234042553192, "acc_norm_stderr": 0.027136349602424056 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.04657047260594963, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.04657047260594963 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7379310344827587, "acc_stderr": 0.036646663372252565, "acc_norm": 0.7379310344827587, "acc_norm_stderr": 0.036646663372252565 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6957671957671958, "acc_stderr": 0.02369541500946309, "acc_norm": 0.6957671957671958, "acc_norm_stderr": 0.02369541500946309 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5396825396825397, "acc_stderr": 0.04458029125470973, "acc_norm": 0.5396825396825397, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.57, "acc_stderr": 0.04975698519562427, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562427 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9, "acc_stderr": 0.017066403719657255, "acc_norm": 0.9, "acc_norm_stderr": 0.017066403719657255 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6699507389162561, "acc_stderr": 0.033085304262282574, "acc_norm": 0.6699507389162561, "acc_norm_stderr": 0.033085304262282574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8545454545454545, "acc_stderr": 0.027530196355066584, "acc_norm": 0.8545454545454545, "acc_norm_stderr": 0.027530196355066584 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9343434343434344, "acc_stderr": 0.01764652667723333, "acc_norm": 0.9343434343434344, "acc_norm_stderr": 0.01764652667723333 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9740932642487047, "acc_stderr": 0.01146452335695318, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.01146452335695318 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8205128205128205, "acc_stderr": 0.019457390787681803, "acc_norm": 0.8205128205128205, "acc_norm_stderr": 0.019457390787681803 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4111111111111111, "acc_stderr": 0.02999992350870669, "acc_norm": 0.4111111111111111, "acc_norm_stderr": 0.02999992350870669 }, "harness|hendrycksTest
