open-llm-leaderboard-old/details_cognitivecomputations__TinyDolphin-2.8-1.1b
收藏数据集概述
数据集简介
该数据集是在模型cognitivecomputations/TinyDolphin-2.8-1.1b的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。
- 运行次数：数据集由1次运行创建。每个运行在每个配置中都有一个特定的分割，分割名称使用运行的时间戳。
- 训练分割："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_cognitivecomputations__TinyDolphin-2.8-1.1b", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-23T11:30:41.082288运行的最新结果：
python { "all": { "acc": 0.2622018497674234, "acc_stderr": 0.030893654783692482, "acc_norm": 0.26309169403239707, "acc_norm_stderr": 0.03165287942154967, "mc1": 0.2252141982864137, "mc1_stderr": 0.014623240768023509, "mc2": 0.36506322642682476, "mc2_stderr": 0.014134362597043171 }, "harness|arc:challenge|25": { "acc": 0.32593856655290104, "acc_stderr": 0.01369743246669324, "acc_norm": 0.3430034129692833, "acc_norm_stderr": 0.013872423223718174 }, "harness|hellaswag|10": { "acc": 0.46126269667396935, "acc_stderr": 0.004974783753309698, "acc_norm": 0.5944035052778331, "acc_norm_stderr": 0.004900036261309041 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621503, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621503 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3111111111111111, "acc_stderr": 0.039992628766177214, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.039992628766177214 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.25, "acc_stderr": 0.03523807393012047, "acc_norm": 0.25, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.20754716981132076, "acc_stderr": 0.024959918028911274, "acc_norm": 0.20754716981132076, "acc_norm_stderr": 0.024959918028911274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2152777777777778, "acc_stderr": 0.03437079344106132, "acc_norm": 0.2152777777777778, "acc_norm_stderr": 0.03437079344106132 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.18, "acc_stderr": 0.03861229196653697, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653697 }, "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": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23699421965317918, "acc_stderr": 0.03242414757483099, "acc_norm": 0.23699421965317918, "acc_norm_stderr": 0.03242414757483099 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237655, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237655 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2170212765957447, "acc_stderr": 0.026947483121496238, "acc_norm": 0.2170212765957447, "acc_norm_stderr": 0.026947483121496238 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.19298245614035087, "acc_stderr": 0.037124548537213684, "acc_norm": 0.19298245614035087, "acc_norm_stderr": 0.037124548537213684 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2689655172413793, "acc_stderr": 0.036951833116502325, "acc_norm": 0.2689655172413793, "acc_norm_stderr": 0.036951833116502325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.26455026455026454, "acc_stderr": 0.02271746789770861, "acc_norm": 0.26455026455026454, "acc_norm_stderr": 0.02271746789770861 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1746031746031746, "acc_stderr": 0.033954900208561116, "acc_norm": 0.1746031746031746, "acc_norm_stderr": 0.033954900208561116 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.25806451612903225, "acc_stderr": 0.02489246917246284, "acc_norm": 0.25806451612903225, "acc_norm_stderr": 0.02489246917246284 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.29064039408866993, "acc_stderr": 0.0319474007226554, "acc_norm": 0.29064039408866993, "acc_norm_stderr": 0.0319474007226554 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25252525252525254, "acc_stderr": 0.030954055470365904, "acc_norm": 0.25252525252525254, "acc_norm_stderr": 0.030954055470365904 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22797927461139897, "acc_stderr": 0.030276909945178256, "acc_norm": 0.22797927461139897, "acc_norm_stderr": 0.030276909945178256 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.22564102564102564, "acc_stderr": 0.021193632525148543, "acc_norm": 0.22564102564102564, "acc_norm_stderr": 0.021193632525148543 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.02696242432507383, "acc_norm": 0.26666666
