open-llm-leaderboard-old/details_01-ai__Yi-34B-Chat
收藏数据集概述
数据集简介
该数据集是在评估模型01-ai/Yi-34B-Chat在Open LLM Leaderboard上的自动创建的。数据集包含64个配置，每个配置对应一个评估任务。
数据集结构
数据集由2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_01-ai__Yi-34B-Chat", "harness_winogrande_5", split="train")
最新结果
以下是最新结果（来自2023-12-05T03:47:25.491369运行）： python { "all": { "acc": 0.7393930299846158, "acc_stderr": 0.028807135333088364, "acc_norm": 0.7489434623723922, "acc_norm_stderr": 0.02935457295982731, "mc1": 0.3843329253365973, "mc1_stderr": 0.017028707301245203, "mc2": 0.5536831362008046, "mc2_stderr": 0.015524186394858242 }, "harness|arc:challenge|25": { "acc": 0.6373720136518771, "acc_stderr": 0.014049106564955012, "acc_norm": 0.6544368600682594, "acc_norm_stderr": 0.013896938461145678 }, "harness|hellaswag|10": { "acc": 0.6536546504680343, "acc_stderr": 0.004748324319714274, "acc_norm": 0.8415654252141008, "acc_norm_stderr": 0.003644017383711605 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7111111111111111, "acc_stderr": 0.03915450630414251, "acc_norm": 0.7111111111111111, "acc_norm_stderr": 0.03915450630414251 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8552631578947368, "acc_stderr": 0.028631951845930387, "acc_norm": 0.8552631578947368, "acc_norm_stderr": 0.028631951845930387 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7924528301886793, "acc_stderr": 0.02495991802891127, "acc_norm": 0.7924528301886793, "acc_norm_stderr": 0.02495991802891127 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8472222222222222, "acc_stderr": 0.030085743248565666, "acc_norm": 0.8472222222222222, "acc_norm_stderr": 0.030085743248565666 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237101, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237101 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6994219653179191, "acc_stderr": 0.034961014811911786, "acc_norm": 0.6994219653179191, "acc_norm_stderr": 0.034961014811911786 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.46078431372549017, "acc_stderr": 0.049598599663841815, "acc_norm": 0.46078431372549017, "acc_norm_stderr": 0.049598599663841815 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.82, "acc_stderr": 0.03861229196653695, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653695 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7659574468085106, "acc_stderr": 0.02767845257821239, "acc_norm": 0.7659574468085106, "acc_norm_stderr": 0.02767845257821239 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5526315789473685, "acc_stderr": 0.046774730044911984, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.046774730044911984 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8, "acc_stderr": 0.0333333333333333, "acc_norm": 0.8, "acc_norm_stderr": 0.0333333333333333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6349206349206349, "acc_stderr": 0.024796060602699965, "acc_norm": 0.6349206349206349, "acc_norm_stderr": 0.024796060602699965 }, "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": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8709677419354839, "acc_stderr": 0.019070889254792767, "acc_norm": 0.8709677419354839, "acc_norm_stderr": 0.019070889254792767 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6206896551724138, "acc_stderr": 0.03413963805906235, "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.03413963805906235 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.81, "acc_stderr": 0.03942772444036625, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8545454545454545, "acc_stderr": 0.027530196355066573, "acc_norm": 0.8545454545454545, "acc_norm_stderr": 0.027530196355066573 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.898989898989899, "acc_stderr": 0.021469735576055343, "acc_norm": 0.898989898989899, "acc_norm_stderr": 0.021469735576055343 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9533678756476683, "acc_stderr": 0.015216761819262585, "acc_norm": 0.9533678756476683, "acc_norm_stderr": 0.015216761819262585 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7846153846153846, "acc_stderr": 0.020843034557462878, "acc_norm": 0.7846153846153846, "acc_norm_stderr": 0.020843034557462878 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35555555555555557, "acc_stderr": 0.029185714949857403, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.029185714949857403 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.83613445378151
