open-llm-leaderboard-old/details_BFauber__lora_llama2-13b_10e5_attn_only
收藏数据集概述
数据集来源
该数据集是在对模型 BFauber/lora_llama2-13b_10e5_attn_only 进行评估运行时自动创建的，评估结果展示在 Open LLM Leaderboard 上。
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，每个运行结果作为一个特定的分割存储在每个配置中，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。
- 汇总结果：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_BFauber__lora_llama2-13b_10e5_attn_only", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-10T01:56:51.335639 运行的最新结果：
python { "all": { "acc": 0.5542783892514437, "acc_stderr": 0.03369405192267445, "acc_norm": 0.5605423625977934, "acc_norm_stderr": 0.03441558227254276, "mc1": 0.26193390452876375, "mc1_stderr": 0.015392118805015023, "mc2": 0.3815579074295717, "mc2_stderr": 0.01395185286827501 }, "harness|arc:challenge|25": { "acc": 0.5656996587030717, "acc_stderr": 0.01448470304885736, "acc_norm": 0.6075085324232082, "acc_norm_stderr": 0.014269634635670735 }, "harness|hellaswag|10": { "acc": 0.6157140011949811, "acc_stderr": 0.004854318994447746, "acc_norm": 0.8208524198366859, "acc_norm_stderr": 0.0038269212990753934 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5333333333333333, "acc_stderr": 0.043097329010363554, "acc_norm": 0.5333333333333333, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5526315789473685, "acc_stderr": 0.04046336883978251, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.04046336883978251 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6075471698113207, "acc_stderr": 0.030052580579557845, "acc_norm": 0.6075471698113207, "acc_norm_stderr": 0.030052580579557845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325582, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325582 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5433526011560693, "acc_stderr": 0.03798106566014498, "acc_norm": 0.5433526011560693, "acc_norm_stderr": 0.03798106566014498 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.04440521906179328, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.04440521906179328 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.044084400227680794, "acc_norm": 0.74, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.44680851063829785, "acc_stderr": 0.0325005368436584, "acc_norm": 0.44680851063829785, "acc_norm_stderr": 0.0325005368436584 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.328042328042328, "acc_stderr": 0.02418049716437691, "acc_norm": 0.328042328042328, "acc_norm_stderr": 0.02418049716437691 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3412698412698413, "acc_stderr": 0.04240799327574925, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.04240799327574925 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.667741935483871, "acc_stderr": 0.0267955608481228, "acc_norm": 0.667741935483871, "acc_norm_stderr": 0.0267955608481228 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4630541871921182, "acc_stderr": 0.035083705204426656, "acc_norm": 0.4630541871921182, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6666666666666666, "acc_stderr": 0.03681050869161551, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.03681050869161551 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6818181818181818, "acc_stderr": 0.0331847733384533, "acc_norm": 0.6818181818181818, "acc_norm_stderr": 0.0331847733384533 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8031088082901554, "acc_stderr": 0.02869787397186068, "acc_norm": 0.8031088082901554, "acc_norm_stderr": 0.02869787397186068 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5230769230769231, "acc_stderr": 0.025323990861736236, "acc_norm": 0.5230769230769231, "acc_norm_stderr": 0.025323990861736236 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.02794045713622842,
