open-llm-leaderboard-old/details_nnheui__pythia-1.4b-sft-full
收藏数据集概述
数据集简介
该数据集是在对模型 nnheui/pythia-1.4b-sft-full 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 数据来源：数据集来自1次运行，每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 最新结果："train" 分割始终指向最新的结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，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_nnheui__pythia-1.4b-sft-full", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要： python { "all": { "acc": 0.2589516508656402, "acc_stderr": 0.030887451070150285, "acc_norm": 0.2601688604419112, "acc_norm_stderr": 0.03164147612275343, "mc1": 0.23990208078335373, "mc1_stderr": 0.014948812679062133, "mc2": 0.3842372864567369, "mc2_stderr": 0.014329362337460367 }, "harness|arc:challenge|25": { "acc": 0.2977815699658703, "acc_stderr": 0.013363080107244487, "acc_norm": 0.3267918088737201, "acc_norm_stderr": 0.013706665975587336 }, "harness|hellaswag|10": { "acc": 0.4016132244572794, "acc_stderr": 0.004892226011836593, "acc_norm": 0.520812587134037, "acc_norm_stderr": 0.004985456752160996 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3111111111111111, "acc_stderr": 0.03999262876617722, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.03999262876617722 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21710526315789475, "acc_stderr": 0.03355045304882922, "acc_norm": 0.21710526315789475, "acc_norm_stderr": 0.03355045304882922 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2490566037735849, "acc_stderr": 0.02661648298050171, "acc_norm": 0.2490566037735849, "acc_norm_stderr": 0.02661648298050171 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.03942772444036625, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23121387283236994, "acc_stderr": 0.0321473730202947, "acc_norm": 0.23121387283236994, "acc_norm_stderr": 0.0321473730202947 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617747, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617747 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.225531914893617, "acc_stderr": 0.027321078417387533, "acc_norm": 0.225531914893617, "acc_norm_stderr": 0.027321078417387533 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.18421052631578946, "acc_stderr": 0.03646758875075566, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.03646758875075566 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2482758620689655, "acc_stderr": 0.036001056927277716, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.036001056927277716 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2751322751322751, "acc_stderr": 0.02300008685906864, "acc_norm": 0.2751322751322751, "acc_norm_stderr": 0.02300008685906864 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15079365079365079, "acc_stderr": 0.03200686497287392, "acc_norm": 0.15079365079365079, "acc_norm_stderr": 0.03200686497287392 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.19, "acc_stderr": 0.03942772444036624, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.22580645161290322, "acc_stderr": 0.023785577884181012, "acc_norm": 0.22580645161290322, "acc_norm_stderr": 0.023785577884181012 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.21182266009852216, "acc_stderr": 0.02874898368994106, "acc_norm": 0.21182266009852216, "acc_norm_stderr": 0.02874898368994106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.26666666666666666, "acc_stderr": 0.03453131801885415, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03453131801885415 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25252525252525254, "acc_stderr": 0.03095405547036589, "acc_norm": 0.25252525252525254, "acc_norm_stderr": 0.03095405547036589 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.23834196891191708, "acc_stderr": 0.030748905363909902, "acc_norm": 0.23834196891191708, "acc_norm_stderr": 0.030748905363909902 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2153846153846154, "acc_stderr": 0.020843034557462878, "acc_norm": 0.2153846153846154, "acc_norm_stderr": 0.020843034557462878 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945277, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945277
