open-llm-leaderboard-old/details_damerajee__Gaja-v1.00
收藏数据集概述
该数据集是在对模型 damerajee/Gaja-v1.00 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。
加载数据集示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_damerajee__Gaja-v1.00", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-29T19:42:27.691927 运行的最新结果：
python { "all": { "acc": 0.4104632836512482, "acc_stderr": 0.03423965153377148, "acc_norm": 0.41631431599382307, "acc_norm_stderr": 0.035127053633139296, "mc1": 0.28886168910648713, "mc1_stderr": 0.01586634640138431, "mc2": 0.4463856836867432, "mc2_stderr": 0.014941359214508863 }, "harness|arc:challenge|25": { "acc": 0.4803754266211604, "acc_stderr": 0.014600132075947084, "acc_norm": 0.5281569965870307, "acc_norm_stderr": 0.014588204105102203 }, "harness|hellaswag|10": { "acc": 0.5711013742282414, "acc_stderr": 0.004939073014754943, "acc_norm": 0.7630950009958176, "acc_norm_stderr": 0.004243145587737571 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4074074074074074, "acc_stderr": 0.04244633238353228, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04046336883978251, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04046336883978251 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.41132075471698115, "acc_stderr": 0.030285009259009798, "acc_norm": 0.41132075471698115, "acc_norm_stderr": 0.030285009259009798 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.375, "acc_stderr": 0.04048439222695598, "acc_norm": 0.375, "acc_norm_stderr": 0.04048439222695598 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "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": 0.18627450980392157, "acc_stderr": 0.038739587141493524, "acc_norm": 0.18627450980392157, "acc_norm_stderr": 0.038739587141493524 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.33191489361702126, "acc_stderr": 0.030783736757745657, "acc_norm": 0.33191489361702126, "acc_norm_stderr": 0.030783736757745657 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.20175438596491227, "acc_stderr": 0.03775205013583638, "acc_norm": 0.20175438596491227, "acc_norm_stderr": 0.03775205013583638 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.41379310344827586, "acc_stderr": 0.04104269211806232, "acc_norm": 0.41379310344827586, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.26455026455026454, "acc_stderr": 0.022717467897708617, "acc_norm": 0.26455026455026454, "acc_norm_stderr": 0.022717467897708617 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.038095238095238106, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.038095238095238106 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.44193548387096776, "acc_stderr": 0.028251557906849734, "acc_norm": 0.44193548387096776, "acc_norm_stderr": 0.028251557906849734 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.270935960591133, "acc_stderr": 0.03127090713297698, "acc_norm": 0.270935960591133, "acc_norm_stderr": 0.03127090713297698 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5212121212121212, "acc_stderr": 0.03900828913737302, "acc_norm": 0.5212121212121212, "acc_norm_stderr": 0.03900828913737302 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.41919191919191917, "acc_stderr": 0.035155207286704175, "acc_norm": 0.41919191919191917, "acc_norm_stderr": 0.035155207286704175 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5440414507772021, "acc_stderr": 0.035944137112724386, "acc_norm": 0.5440414507772021, "acc_norm_stderr": 0.035944137112724386 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.38461538461538464, "acc_stderr": 0.024666744915187222, "acc_norm": 0.38461538461538464, "acc_norm_stderr": 0.024666744915187222 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945284, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945284 }, "harness|hendrycksTest-high_school_microeconomics|
