open-llm-leaderboard-old/details_abhinand__TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft
收藏数据集概述
数据集摘要
该数据集是在评估模型 abhinand/TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。
- 运行次数：数据集由1次运行创建。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。
- 训练分割："train" 分割总是指向最新的结果。
- 结果配置：一个额外的配置 "results" 存储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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_abhinand__TinyLlama-1.1B-OpenHermes-2.5-Chat-v0.1-sft", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-09T17:14:23.024715 运行 的最新结果：
python { "all": { "acc": 0.25230068016115625, "acc_stderr": 0.030498670802431283, "acc_norm": 0.25259575273482276, "acc_norm_stderr": 0.03119964119680332, "mc1": 0.21909424724602203, "mc1_stderr": 0.014480038578757442, "mc2": 0.3621952768373166, "mc2_stderr": 0.013699293770021182 }, "harness|arc:challenge|25": { "acc": 0.30802047781569963, "acc_stderr": 0.01349142951729204, "acc_norm": 0.3378839590443686, "acc_norm_stderr": 0.01382204792228351 }, "harness|hellaswag|10": { "acc": 0.4411471818362876, "acc_stderr": 0.004955095096264714, "acc_norm": 0.5872336188010356, "acc_norm_stderr": 0.004913253031155673 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.22962962962962963, "acc_stderr": 0.03633384414073465, "acc_norm": 0.22962962962962963, "acc_norm_stderr": 0.03633384414073465 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21052631578947367, "acc_stderr": 0.03317672787533157, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.03317672787533157 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2339622641509434, "acc_stderr": 0.02605529690115292, "acc_norm": 0.2339622641509434, "acc_norm_stderr": 0.02605529690115292 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2361111111111111, "acc_stderr": 0.03551446610810826, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.16, "acc_stderr": 0.0368452949177471, "acc_norm": 0.16, "acc_norm_stderr": 0.0368452949177471 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.1676300578034682, "acc_stderr": 0.028481963032143377, "acc_norm": 0.1676300578034682, "acc_norm_stderr": 0.028481963032143377 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617746, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617746 }, "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": 0.251063829787234, "acc_stderr": 0.028346963777162452, "acc_norm": 0.251063829787234, "acc_norm_stderr": 0.028346963777162452 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2206896551724138, "acc_stderr": 0.03455930201924811, "acc_norm": 0.2206896551724138, "acc_norm_stderr": 0.03455930201924811 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2671957671957672, "acc_stderr": 0.02278967314577657, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.02278967314577657 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.19047619047619047, "acc_stderr": 0.035122074123020534, "acc_norm": 0.19047619047619047, "acc_norm_stderr": 0.035122074123020534 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.15, "acc_stderr": 0.0358870281282637, "acc_norm": 0.15, "acc_norm_stderr": 0.0358870281282637 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.20967741935483872, "acc_stderr": 0.023157879349083522, "acc_norm": 0.20967741935483872, "acc_norm_stderr": 0.023157879349083522 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.19704433497536947, "acc_stderr": 0.02798672466673621, "acc_norm": 0.19704433497536947, "acc_norm_stderr": 0.02798672466673621 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2909090909090909, "acc_stderr": 0.03546563019624336, "acc_norm": 0.2909090909090909, "acc_norm_stderr": 0.03546563019624336 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.21212121212121213, "acc_stderr": 0.02912652283458682, "acc_norm": 0.21212121212121213, "acc_norm_stderr": 0.02912652283458682 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.21761658031088082, "acc_stderr": 0.02977866303775295, "acc_norm": 0.21761658031088082, "acc_norm_stderr": 0.02977866303775295 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.23846153846153847, "acc_stderr": 0.021606294494647727, "acc_norm": 0.23846153846153847, "acc_norm_stderr": 0.021606294494647727 }, "harness|hendrycksTest-high_school_mathematics|5": {
