open-llm-leaderboard-old/details_SF-Foundation__Ein-72B-v0.12
收藏数据集概述
数据集摘要
该数据集是在模型 SF-Foundation/Ein-72B-v0.12 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 63 个配置组成，每个配置对应一个评估任务。
数据集结构
- 配置数量：63
- 数据来源：1 次运行
- 数据分割：每个配置包含特定运行的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置："results" 存储所有运行结果的聚合，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_SF-Foundation__Ein-72B-v0.12", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-13T11:06:19.237402 运行的最新结果：
python { "all": { "acc": 0.7720004576068558, "acc_stderr": 0.028018920061937066, "acc_norm": 0.77366212968727, "acc_norm_stderr": 0.028576972189266775, "mc1": 0.6597307221542228, "mc1_stderr": 0.016586304901762553, "mc2": 0.7778465654225306, "mc2_stderr": 0.013819882710780051 }, "harness|arc:challenge|25": { "acc": 0.7406143344709898, "acc_stderr": 0.01280827357392709, "acc_norm": 0.7619453924914675, "acc_norm_stderr": 0.0124457700280262 }, "harness|hellaswag|10": { "acc": 0.7251543517227644, "acc_stderr": 0.004455240755811573, "acc_norm": 0.8946425014937264, "acc_norm_stderr": 0.003063860621772738 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7185185185185186, "acc_stderr": 0.038850042458002526, "acc_norm": 0.7185185185185186, "acc_norm_stderr": 0.038850042458002526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.881578947368421, "acc_stderr": 0.026293995855474928, "acc_norm": 0.881578947368421, "acc_norm_stderr": 0.026293995855474928 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.82, "acc_stderr": 0.038612291966536955, "acc_norm": 0.82, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8377358490566038, "acc_stderr": 0.02269148287203535, "acc_norm": 0.8377358490566038, "acc_norm_stderr": 0.02269148287203535 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9375, "acc_stderr": 0.02024219611347799, "acc_norm": 0.9375, "acc_norm_stderr": 0.02024219611347799 }, "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": 0.61, "acc_stderr": 0.04902071300001974, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7456647398843931, "acc_stderr": 0.0332055644308557, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5686274509803921, "acc_stderr": 0.04928099597287534, "acc_norm": 0.5686274509803921, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.03942772444036622, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036622 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7957446808510639, "acc_stderr": 0.026355158413349417, "acc_norm": 0.7957446808510639, "acc_norm_stderr": 0.026355158413349417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6052631578947368, "acc_stderr": 0.045981880578165414, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.045981880578165414 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7793103448275862, "acc_stderr": 0.03455930201924811, "acc_norm": 0.7793103448275862, "acc_norm_stderr": 0.03455930201924811 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6851851851851852, "acc_stderr": 0.023919984164047732, "acc_norm": 0.6851851851851852, "acc_norm_stderr": 0.023919984164047732 }, "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": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8870967741935484, "acc_stderr": 0.0180036033258636, "acc_norm": 0.8870967741935484, "acc_norm_stderr": 0.0180036033258636 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6650246305418719, "acc_stderr": 0.033208527423483104, "acc_norm": 0.6650246305418719, "acc_norm_stderr": 0.033208527423483104 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.82, "acc_stderr": 0.038612291966536934, "acc_norm": 0.82, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.027045948825865394, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.027045948825865394 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9393939393939394, "acc_stderr": 0.016999994927421592, "acc_norm": 0.9393939393939394, "acc_norm_stderr": 0.016999994927421592 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9844559585492227, "acc_stderr": 0.008927492715084315, "acc_norm": 0.9844559585492227, "acc_norm_stderr": 0.008927492715084315 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8102564102564103, "acc_stderr": 0.01988016540658877, "acc_norm": 0.8102564102564103, "acc_norm_stderr": 0.01988016540658877 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.45555555555555555, "acc_stderr": 0.03036486250482443, "acc_norm": 0.45555555555555555, "acc_norm_stderr": 0.03036486250482443 }, "harness|hendrycksTest-high_school_
