open-llm-leaderboard-old/details_mlabonne__Gemmalpaca-2B
收藏数据集概述
数据集简介
该数据集是在评估模型 mlabonne/Gemmalpaca-2B 在 Open LLM Leaderboard 上的自动创建的。
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。
- 数据集从 1 次运行中创建,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,用于计算和显示聚合指标在 Open LLM Leaderboard 上。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_mlabonne__Gemmalpaca-2B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-23T19:16:03.621570 运行的最新结果:
python { "all": { "acc": 0.3683285110970895, "acc_stderr": 0.03391182933419809, "acc_norm": 0.3710380488758352, "acc_norm_stderr": 0.034683304905626926, "mc1": 0.2533659730722154, "mc1_stderr": 0.015225899340826845, "mc2": 0.412366178724327, "mc2_stderr": 0.014754217093653488 }, "harness|arc:challenge|25": { "acc": 0.4726962457337884, "acc_stderr": 0.014589589101985994, "acc_norm": 0.4872013651877133, "acc_norm_stderr": 0.014606603181012534 }, "harness|hellaswag|10": { "acc": 0.5421230830511851, "acc_stderr": 0.004972042602001383, "acc_norm": 0.7136028679545907, "acc_norm_stderr": 0.004511533039406226 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, ... }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2024_02_23T19_16_03.621570
- path: **/details_harness|arc:challenge|25_2024-02-23T19-16-03.621570.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2024-02-23T19-16-03.621570.parquet
- split: 2024_02_23T19_16_03.621570
-
config_name: harness_gsm8k_5
- split: 2024_02_23T19_16_03.621570
- path: **/details_harness|gsm8k|5_2024-02-23T19-16-03.621570.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2024-02-23T19-16-03.621570.parquet
- split: 2024_02_23T19_16_03.621570
-
config_name: harness_hellaswag_10
- split: 2024_02_23T19_16_03.621570
- path: **/details_harness|hellaswag|10_2024-02-23T19-16-03.621570.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2024-02-23T19-16-03.621570.parquet
- split: 2024_02_23T19_16_03.621570
-
config_name: harness_hendrycksTest_5
- split: 2024_02_23T19_16_03.621570
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-02-23T19-16-03.621570.parquet
- ...
- path:
- split: latest
- path:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-02-23T19-16-03.621570.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-02-23T19-16-03.621570.parquet
- ...
- path:
- split: 2024_02_23T19_16_03.621570



