open-llm-leaderboard-old/details_Minami-su__roleplay_alpaca_llama_lora
收藏数据集概述
该数据集是在评估模型 Minami-su/roleplay_alpaca_llama_lora 在 Open LLM Leaderboard 上的运行过程中自动创建的。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。
结果配置
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 Open LLM Leaderboard 上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Minami-su__roleplay_alpaca_llama_lora", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-25T12:56:10.791035 运行的最新结果：
python { "all": { "acc": 0.26849543102239015, "acc_stderr": 0.030962758029676598, "acc_norm": 0.27030533183140004, "acc_norm_stderr": 0.03179230056889492, "mc1": 0.2460220318237454, "mc1_stderr": 0.015077219200662578, "mc2": 0.48633711369293997, "mc2_stderr": 0.01574877558479582 }, "harness|arc:challenge|25": { "acc": 0.2158703071672355, "acc_stderr": 0.012022975360030684, "acc_norm": 0.2764505119453925, "acc_norm_stderr": 0.013069662474252428 }, "harness|hellaswag|10": { "acc": 0.25582553276239794, "acc_stderr": 0.004354325017137537, "acc_norm": 0.2599083847839076, "acc_norm_stderr": 0.004376877619234125 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.22962962962962963, "acc_stderr": 0.03633384414073461, "acc_norm": 0.22962962962962963, "acc_norm_stderr": 0.03633384414073461 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3355263157894737, "acc_stderr": 0.03842498559395268, "acc_norm": 0.3355263157894737, "acc_norm_stderr": 0.03842498559395268 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2981132075471698, "acc_stderr": 0.028152837942493857, "acc_norm": 0.2981132075471698, "acc_norm_stderr": 0.028152837942493857 }, "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": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "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": 0.3352601156069364, "acc_stderr": 0.03599586301247078, "acc_norm": 0.3352601156069364, "acc_norm_stderr": 0.03599586301247078 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082633, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082633 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.18, "acc_stderr": 0.038612291966536955, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536955 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.20851063829787234, "acc_stderr": 0.026556982117838728, "acc_norm": 0.20851063829787234, "acc_norm_stderr": 0.026556982117838728 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813344, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813344 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2671957671957672, "acc_stderr": 0.022789673145776564, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.022789673145776564 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.02645087448904277, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.02645087448904277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.03161856335358609, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.03161856335358609 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2545454545454545, "acc_stderr": 0.03401506715249039, "acc_norm": 0.2545454545454545, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.35353535353535354, "acc_stderr": 0.03406086723547153, "acc_norm": 0.35353535353535354, "acc_norm_stderr": 0.03406086723547153 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.36787564766839376, "acc_stderr": 0.03480175668466036, "acc_norm": 0.36787564766839376, "acc_norm_stderr": 0.03480175668466036 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3641025641025641, "acc_stderr": 0.02439667298509477, "acc_norm": 0.3641025641025641, "acc_norm_stderr": 0.02439667298509477 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.026842057873833706, "acc_norm": 0
