open-llm-leaderboard-old/details_Dans-DiscountModels__TinyLlama-1.1B-FFT-Test2
收藏数据集概述
数据集摘要
该数据集是在评估模型 Dans-DiscountModels/TinyLlama-1.1B-FFT-Test2 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，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。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 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_Dans-DiscountModels__TinyLlama-1.1B-FFT-Test2", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2023-12-18T02:54:33.981160 的运行： python { "all": { "acc": 0.2607212816484538, "acc_stderr": 0.030867007452377485, "acc_norm": 0.26236232884330074, "acc_norm_stderr": 0.03165482907989167, "mc1": 0.20563035495716034, "mc1_stderr": 0.014148482219460972, "mc2": 0.3631613697388407, "mc2_stderr": 0.013778296923024373 }, "harness|arc:challenge|25": { "acc": 0.31399317406143346, "acc_stderr": 0.013562691224726291, "acc_norm": 0.34215017064846415, "acc_norm_stderr": 0.013864152159177278 }, "harness|hellaswag|10": { "acc": 0.44054969129655447, "acc_stderr": 0.004954384702021655, "acc_norm": 0.5795658235411273, "acc_norm_stderr": 0.004926198483948714 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.17777777777777778, "acc_stderr": 0.03302789859901717, "acc_norm": 0.17777777777777778, "acc_norm_stderr": 0.03302789859901717 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21710526315789475, "acc_stderr": 0.03355045304882921, "acc_norm": 0.21710526315789475, "acc_norm_stderr": 0.03355045304882921 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.27547169811320754, "acc_stderr": 0.027495663683724077, "acc_norm": 0.27547169811320754, "acc_norm_stderr": 0.027495663683724077 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2708333333333333, "acc_stderr": 0.03716177437566017, "acc_norm": 0.2708333333333333, "acc_norm_stderr": 0.03716177437566017 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.03942772444036624, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23121387283236994, "acc_stderr": 0.03214737302029469, "acc_norm": 0.23121387283236994, "acc_norm_stderr": 0.03214737302029469 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808778, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808778 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2553191489361702, "acc_stderr": 0.0285048564705142, "acc_norm": 0.2553191489361702, "acc_norm_stderr": 0.0285048564705142 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.04142439719489362, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.04142439719489362 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.21379310344827587, "acc_stderr": 0.034165204477475494, "acc_norm": 0.21379310344827587, "acc_norm_stderr": 0.034165204477475494 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.20634920634920634, "acc_stderr": 0.020842290930114683, "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.020842290930114683 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2619047619047619, "acc_stderr": 0.03932537680392871, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.03932537680392871 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.21935483870967742, "acc_stderr": 0.02354079935872329, "acc_norm": 0.21935483870967742, "acc_norm_stderr": 0.02354079935872329 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.21182266009852216, "acc_stderr": 0.02874898368994107, "acc_norm": 0.21182266009852216, "acc_norm_stderr": 0.02874898368994107 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.24242424242424243, "acc_stderr": 0.03346409881055953, "acc_norm": 0.24242424242424243, "acc_norm_stderr": 0.03346409881055953 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.22727272727272727, "acc_stderr": 0.029857515673386396, "acc_norm": 0.22727272727272727, "acc_norm_stderr": 0.029857515673386396 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22797927461139897, "acc_stderr": 0.030276909945178263, "acc_norm": 0.22797927461139897, "acc_norm_stderr": 0.030276909945178263 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.24358974358974358, "acc_stderr": 0.02176373368417392, "acc_norm": 0.24358974358974358, "acc_norm_stderr": 0.02176373368417392 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2518518518518518, "acc_stderr": 0.026466117538959912, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.026466117538959912 }, "harness|hendrycksTest
