open-llm-leaderboard-old/details_MaziyarPanahi__WizardLM-Math-70B-TIES-v0.1
收藏数据集概述
数据集名称
Evaluation run of MaziyarPanahi/WizardLM-Math-70B-TIES-v0.1
数据集描述
该数据集是在评估模型 MaziyarPanahi/WizardLM-Math-70B-TIES-v0.1 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。
- 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_MaziyarPanahi__WizardLM-Math-70B-TIES-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-18T06:49:50.553009 运行的最新结果：
python { "all": { "acc": 0.6868282613819305, "acc_stderr": 0.030371866427473967, "acc_norm": 0.695311288530275, "acc_norm_stderr": 0.030984285786669577, "mc1": 0.36964504283965727, "mc1_stderr": 0.01689818070697388, "mc2": 0.5360987678643523, "mc2_stderr": 0.014938153988985473 }, "harness|arc:challenge|25": { "acc": 0.6424914675767918, "acc_stderr": 0.014005494275916573, "acc_norm": 0.6851535836177475, "acc_norm_stderr": 0.01357265770308495 }, "harness|hellaswag|10": { "acc": 0.6836287592113125, "acc_stderr": 0.004641092001425294, "acc_norm": 0.8686516630153356, "acc_norm_stderr": 0.0033709059327855567 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595852, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595852 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8026315789473685, "acc_stderr": 0.03238981601699397, "acc_norm": 0.8026315789473685, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7471698113207547, "acc_stderr": 0.026749899771241214, "acc_norm": 0.7471698113207547, "acc_norm_stderr": 0.026749899771241214 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8194444444444444, "acc_stderr": 0.032166008088022675, "acc_norm": 0.8194444444444444, "acc_norm_stderr": 0.032166008088022675 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "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": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.047551296160629475, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.047551296160629475 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768079, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6893617021276596, "acc_stderr": 0.03025123757921317, "acc_norm": 0.6893617021276596, "acc_norm_stderr": 0.03025123757921317 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.046151869625837026, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.046151869625837026 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6068965517241379, "acc_stderr": 0.040703290137070705, "acc_norm": 0.6068965517241379, "acc_norm_stderr": 0.040703290137070705 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4312169312169312, "acc_stderr": 0.0255064816981382, "acc_norm": 0.4312169312169312, "acc_norm_stderr": 0.0255064816981382 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5, "acc_stderr": 0.04472135954999579, "acc_norm": 0.5, "acc_norm_stderr": 0.04472135954999579 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8193548387096774, "acc_stderr": 0.021886178567172527, "acc_norm": 0.8193548387096774, "acc_norm_stderr": 0.021886178567172527 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5320197044334976, "acc_stderr": 0.03510766597959217, "acc_norm": 0.5320197044334976, "acc_norm_stderr": 0.03510766597959217 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8121212121212121, "acc_stderr": 0.03050193405942914, "acc_norm": 0.8121212121212121, "acc_norm_stderr": 0.03050193405942914 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8888888888888888, "acc_stderr": 0.022390787638216773, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.022390787638216773 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.927461139896373, "acc_stderr": 0.018718998520678185, "acc_norm": 0.927461139896373, "acc_norm_stderr": 0.018718998520678185 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7230769230769231, "acc_stderr": 0.022688042352424994, "acc_norm": 0.7230769230769231, "acc_norm_stderr": 0.022688042352424994 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742
