open-llm-leaderboard-old/details_invalid-coder__TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo
收藏数据集概述
数据集简介
该数据集是在评估模型invalid-coder/TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo在Open LLM Leaderboard上的运行过程中自动创建的。
数据集组成
- 数据集包含63个配置，每个配置对应一个评估任务。
- 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。
- 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_invalid-coder__TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo", "harness_winogrande_5", split="train")
最新结果
以下是2024-03-30T15:13:38.324226的最新结果：
python { "all": { "acc": 0.2735286860324725, "acc_stderr": 0.03143769848552324, "acc_norm": 0.2754881804383971, "acc_norm_stderr": 0.03222142068698204, "mc1": 0.22766217870257038, "mc1_stderr": 0.01467925503211107, "mc2": 0.38078325221080583, "mc2_stderr": 0.01386769746146585 }, "harness|arc:challenge|25": { "acc": 0.30887372013651876, "acc_stderr": 0.013501770929344003, "acc_norm": 0.3302047781569966, "acc_norm_stderr": 0.013743085603760427 }, "harness|hellaswag|10": { "acc": 0.4447321250746863, "acc_stderr": 0.004959204773046204, "acc_norm": 0.5999800836486756, "acc_norm_stderr": 0.004889007921214687 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2074074074074074, "acc_stderr": 0.03502553170678318, "acc_norm": 0.2074074074074074, "acc_norm_stderr": 0.03502553170678318 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.14473684210526316, "acc_stderr": 0.028631951845930394, "acc_norm": 0.14473684210526316, "acc_norm_stderr": 0.028631951845930394 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.04408440022768078, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.27547169811320754, "acc_stderr": 0.027495663683724064, "acc_norm": 0.27547169811320754, "acc_norm_stderr": 0.027495663683724064 }, "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": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.31213872832369943, "acc_stderr": 0.03533133389323657, "acc_norm": 0.31213872832369943, "acc_norm_stderr": 0.03533133389323657 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617749, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617749 }, "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": 0.28936170212765955, "acc_stderr": 0.02964400657700962, "acc_norm": 0.28936170212765955, "acc_norm_stderr": 0.02964400657700962 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21052631578947367, "acc_stderr": 0.03835153954399419, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.03835153954399419 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2620689655172414, "acc_stderr": 0.036646663372252565, "acc_norm": 0.2620689655172414, "acc_norm_stderr": 0.036646663372252565 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.291005291005291, "acc_stderr": 0.02339382650048488, "acc_norm": 0.291005291005291, "acc_norm_stderr": 0.02339382650048488 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "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": 0.25161290322580643, "acc_stderr": 0.02468597928623997, "acc_norm": 0.25161290322580643, "acc_norm_stderr": 0.02468597928623997 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2561576354679803, "acc_stderr": 0.0307127300709826, "acc_norm": 0.2561576354679803, "acc_norm_stderr": 0.0307127300709826 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.32727272727272727, "acc_stderr": 0.03663974994391243, "acc_norm": 0.32727272727272727, "acc_norm_stderr": 0.03663974994391243 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2474747474747475, "acc_stderr": 0.0307463007421245, "acc_norm": 0.2474747474747475, "acc_norm_stderr": 0.0307463007421245 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.24352331606217617, "acc_stderr": 0.03097543638684543, "acc_norm": 0.24352331606217617, "acc_norm_stderr": 0.03097543638684543 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.30256410256410254, "acc_stderr": 0.02329088805377274, "acc_norm": 0.30256410256410254, "acc_norm_stderr": 0.02329088805377274 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.255555555
