open-llm-leaderboard/details_openlm-research__open_llama_3b
收藏资源简介:
该数据集是在Open LLM Leaderboard上对openlm-research/open_llama_3b模型进行评估时自动创建的。数据集包含122个配置,每个配置对应一个评估任务。数据集由6次运行生成,每次运行的结果作为特定配置中的一个分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个名为results的配置存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。
This dataset was automatically created during the evaluation of the openlm-research/open_llama_3b model on the Open LLM Leaderboard. It contains 122 configurations, each corresponding to one evaluation task. The dataset is generated from 6 runs, where the results of each run serve as a data split under the corresponding configuration, with the split name being the timestamp of the run. The "train" split always points to the most recent evaluation results. In addition, there is a configuration named "results" that stores the aggregated results of all runs, which are used to calculate and display the aggregated metrics on the Open LLM Leaderboard.
数据集概述
数据集简介
该数据集是在对模型 openlm-research/open_llama_3b 进行评估运行期间自动创建的,用于 Open LLM Leaderboard 的评估。
数据集组成
- 数据集包含 122 个配置,每个配置对应一个评估任务。
- 数据集从 6 次运行中创建,每次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_openlm-research__open_llama_3b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-18T03:50:40.523576 运行的最新结果: python { "all": { "em": 0.0005243288590604027, "em_stderr": 0.00023443780464835776, "f1": 0.050632340604026965, "f1_stderr": 0.001271781500579302, "acc": 0.32587350322198844, "acc_stderr": 0.00764164157289629 }, "harness|drop|3": { "em": 0.0005243288590604027, "em_stderr": 0.00023443780464835776, "f1": 0.050632340604026965, "f1_stderr": 0.001271781500579302 }, "harness|gsm8k|5": { "acc": 0.004548900682335102, "acc_stderr": 0.0018535550440036204 }, "harness|winogrande|5": { "acc": 0.6471981057616417, "acc_stderr": 0.01342972810178896 } }
配置详情
-
config_name: harness_arc_challenge_25
- split: 2023_07_18T11_22_49.433588
- path: **/details_harness|arc:challenge|25_2023-07-18T11:22:49.433588.parquet
- split: 2023_07_19T10_43_17.176281
- path: **/details_harness|arc:challenge|25_2023-07-19T10:43:17.176281.parquet
- split: latest
- path: **/details_harness|arc:challenge|25_2023-07-19T10:43:17.176281.parquet
- split: 2023_07_18T11_22_49.433588
-
config_name: harness_drop_3
- split: 2023_10_18T03_50_40.523576
- path: **/details_harness|drop|3_2023-10-18T03-50-40.523576.parquet
- split: latest
- path: **/details_harness|drop|3_2023-10-18T03-50-40.523576.parquet
- split: 2023_10_18T03_50_40.523576
-
config_name: harness_gsm8k_5
- split: 2023_10_18T03_50_40.523576
- path: **/details_harness|gsm8k|5_2023-10-18T03-50-40.523576.parquet
- split: latest
- path: **/details_harness|gsm8k|5_2023-10-18T03-50-40.523576.parquet
- split: 2023_10_18T03_50_40.523576
-
config_name: harness_hellaswag_10
- split: 2023_07_18T11_22_49.433588
- path: **/details_harness|hellaswag|10_2023-07-18T11:22:49.433588.parquet
- split: 2023_07_19T10_43_17.176281
- path: **/details_harness|hellaswag|10_2023-07-19T10:43:17.176281.parquet
- split: latest
- path: **/details_harness|hellaswag|10_2023-07-19T10:43:17.176281.parquet
- split: 2023_07_18T11_22_49.433588
-
config_name: harness_hendrycksTest_5
- split: 2023_07_18T11_22_49.433588
- path: **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-anatomy|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-astronomy|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-business_ethics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-college_biology|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-college_chemistry|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-college_computer_science|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-college_mathematics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-college_medicine|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-college_physics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-computer_security|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-econometrics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-formal_logic|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-global_facts|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_biology|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_geography|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_physics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-human_aging|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-human_sexuality|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-international_law|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-jurisprudence|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-machine_learning|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-management|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-marketing|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-medical_genetics|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-miscellaneous|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-moral_disputes|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-18T11:22:49.433588.parquet
- path: **/details_harness|hendry
- split: 2023_07_18T11_22_49.433588



