open-llm-leaderboard-old/details_Azure99__blossom-v4-yi-34b
收藏数据集概述
数据集摘要
该数据集是在对模型 Azure99/blossom-v4-yi-34b 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，每个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_Azure99__blossom-v4-yi-34b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-19T21:45:41.713971 运行的最新结果：
python { "all": { "acc": 0.739671394200245, "acc_stderr": 0.028886763798650763, "acc_norm": 0.7438543161850231, "acc_norm_stderr": 0.029435791719275347, "mc1": 0.4222766217870257, "mc1_stderr": 0.017290733254248174, "mc2": 0.5789435735270319, "mc2_stderr": 0.015680201588503598 }, "harness|arc:challenge|25": { "acc": 0.6348122866894198, "acc_stderr": 0.014070265519268802, "acc_norm": 0.6680887372013652, "acc_norm_stderr": 0.013760988200880534 }, "harness|hellaswag|10": { "acc": 0.6447918741286597, "acc_stderr": 0.004775982650355924, "acc_norm": 0.844353714399522, "acc_norm_stderr": 0.0036177879347477483 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.725925925925926, "acc_stderr": 0.03853254836552003, "acc_norm": 0.725925925925926, "acc_norm_stderr": 0.03853254836552003 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8618421052631579, "acc_stderr": 0.028081042939576552, "acc_norm": 0.8618421052631579, "acc_norm_stderr": 0.028081042939576552 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.81, "acc_stderr": 0.03942772444036622, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036622 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7849056603773585, "acc_stderr": 0.025288394502891366, "acc_norm": 0.7849056603773585, "acc_norm_stderr": 0.025288394502891366 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8680555555555556, "acc_stderr": 0.02830096838204443, "acc_norm": 0.8680555555555556, "acc_norm_stderr": 0.02830096838204443 }, "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": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.04975698519562429, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562429 }, "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": 0.45098039215686275, "acc_stderr": 0.04951218252396264, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.04951218252396264 }, "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": 0.774468085106383, "acc_stderr": 0.027321078417387536, "acc_norm": 0.774468085106383, "acc_norm_stderr": 0.027321078417387536 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.543859649122807, "acc_stderr": 0.046854730419077895, "acc_norm": 0.543859649122807, "acc_norm_stderr": 0.046854730419077895 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7793103448275862, "acc_stderr": 0.034559302019248124, "acc_norm": 0.7793103448275862, "acc_norm_stderr": 0.034559302019248124 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6375661375661376, "acc_stderr": 0.024757473902752045, "acc_norm": 0.6375661375661376, "acc_norm_stderr": 0.024757473902752045 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5714285714285714, "acc_stderr": 0.04426266681379909, "acc_norm": 0.5714285714285714, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8774193548387097, "acc_stderr": 0.01865672099178941, "acc_norm": 0.8774193548387097, "acc_norm_stderr": 0.01865672099178941 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6059113300492611, "acc_stderr": 0.034381579670365446, "acc_norm": 0.6059113300492611, "acc_norm_stderr": 0.034381579670365446 }, "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": 0.8606060606060606, "acc_stderr": 0.027045948825865387, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865387 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9040404040404041, "acc_stderr": 0.020984808610047926, "acc_norm": 0.9040404040404041, "acc_norm_stderr": 0.020984808610047926 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9585492227979274, "acc_stderr": 0.014385432857476458, "acc_norm": 0.9585492227979274, "acc_norm_stderr": 0.014385432857476458 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7666666666666667, "acc_stderr": 0.021444547301560486, "acc_norm": 0.7666666666666667, "acc_norm_stderr": 0.021444547301560486 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.028820884666253255, "acc_norm": 0.337037037037037
