open-llm-leaderboard-old/details_freecs__Tiny-Llama-3-7b
收藏数据集概述
数据集简介
该数据集是在评估模型freecs/Tiny-Llama-3-7b在Open LLM Leaderboard上的自动创建的。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"分割总是指向最新的结果。
额外配置
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_freecs__Tiny-Llama-3-7b", "harness_winogrande_5", split="train")
最新结果
以下是2024-01-17T03:01:17.599813运行的最新结果: python { "all": { "acc": 0.250629407659835, "acc_stderr": 0.030466481126384053, "acc_norm": 0.2521914286046078, "acc_norm_stderr": 0.031247424038738997, "mc1": 0.23623011015911874, "mc1_stderr": 0.014869755015871119, "mc2": 0.3803046918315385, "mc2_stderr": 0.014776905887343683 }, "harness|arc:challenge|25": { "acc": 0.29266211604095566, "acc_stderr": 0.013295916103619418, "acc_norm": 0.3464163822525597, "acc_norm_stderr": 0.013905011180063251 }, "harness|hellaswag|10": { "acc": 0.42630950009958174, "acc_stderr": 0.004935291975579184, "acc_norm": 0.563931487751444, "acc_norm_stderr": 0.004948824501355487 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, # 其他任务的结果... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_01_17T03_01_17.599813
- path: **/details_harness|arc:challenge|25_2024-01-17T03-01-17.599813.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-01-17T03-01-17.599813.parquet
- split: 2024_01_17T03_01_17.599813
-
config_name: harness_gsm8k_5
- split: 2024_01_17T03_01_17.599813
- path: **/details_harness|gsm8k|5_2024-01-17T03-01-17.599813.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-01-17T03-01-17.599813.parquet
- split: 2024_01_17T03_01_17.599813
-
config_name: harness_hellaswag_10
- split: 2024_01_17T03_01_17.599813
- path: **/details_harness|hellaswag|10_2024-01-17T03-01-17.599813.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-01-17T03-01-17.599813.parquet
- split: 2024_01_17T03_01_17.599813
-
config_name: harness_hendrycksTest_5
- split: 2024_01_17T03_01_17.599813
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-management|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-01-17T03-01-17.599813.parquet
- **/details_harness|hendrycksTest-professional_medicine|5
- path:
- split: 2024_01_17T03_01_17.599813



