five

open-llm-leaderboard/details_winglian__Llama-2-3b-hf

收藏
Hugging Face2023-10-24 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_winglian__Llama-2-3b-hf
下载链接
链接失效反馈
官方服务:
资源简介:
--- pretty_name: Evaluation run of winglian/Llama-2-3b-hf dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [winglian/Llama-2-3b-hf](https://huggingface.co/winglian/Llama-2-3b-hf) on the\ \ [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\ \nThe dataset is composed of 64 configuration, each one coresponding to one of the\ \ evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be\ \ found as a specific split in each configuration, the split being named using the\ \ timestamp of the run.The \"train\" split is always pointing to the latest results.\n\ \nAn additional configuration \"results\" store all the aggregated results of the\ \ run (and is used to compute and display the agregated metrics on the [Open LLM\ \ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\ \nTo load the details from a run, you can for instance do the following:\n```python\n\ from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_winglian__Llama-2-3b-hf\"\ ,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\ These are the [latest results from run 2023-10-24T02:31:53.066054](https://huggingface.co/datasets/open-llm-leaderboard/details_winglian__Llama-2-3b-hf/blob/main/results_2023-10-24T02-31-53.066054.json)(note\ \ that their might be results for other tasks in the repos if successive evals didn't\ \ cover the same tasks. You find each in the results and the \"latest\" split for\ \ each eval):\n\n```python\n{\n \"all\": {\n \"em\": 0.01960989932885906,\n\ \ \"em_stderr\": 0.0014199622282460517,\n \"f1\": 0.026280411073825484,\n\ \ \"f1_stderr\": 0.0015385339771850702,\n \"acc\": 0.24822415153906865,\n\ \ \"acc_stderr\": 0.007026065573457934\n },\n \"harness|drop|3\": {\n\ \ \"em\": 0.01960989932885906,\n \"em_stderr\": 0.0014199622282460517,\n\ \ \"f1\": 0.026280411073825484,\n \"f1_stderr\": 0.0015385339771850702\n\ \ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.0,\n \"acc_stderr\"\ : 0.0\n },\n \"harness|winogrande|5\": {\n \"acc\": 0.4964483030781373,\n\ \ \"acc_stderr\": 0.014052131146915867\n }\n}\n```" repo_url: https://huggingface.co/winglian/Llama-2-3b-hf leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard point_of_contact: clementine@hf.co configs: - config_name: harness_arc_challenge_25 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|arc:challenge|25_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|arc:challenge|25_2023-10-03T14-29-31.026296.parquet' - config_name: harness_drop_3 data_files: - split: 2023_10_24T02_31_53.066054 path: - '**/details_harness|drop|3_2023-10-24T02-31-53.066054.parquet' - split: latest path: - '**/details_harness|drop|3_2023-10-24T02-31-53.066054.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2023_10_24T02_31_53.066054 path: - '**/details_harness|gsm8k|5_2023-10-24T02-31-53.066054.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2023-10-24T02-31-53.066054.parquet' - config_name: harness_hellaswag_10 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hellaswag|10_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hellaswag|10_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-management|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-management|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-10-03T14-29-31.026296.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_abstract_algebra_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_anatomy_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-anatomy|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-anatomy|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_astronomy_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-astronomy|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-astronomy|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_business_ethics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_clinical_knowledge_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_college_biology_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-college_biology|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_biology|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_college_chemistry_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_college_computer_science_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_college_mathematics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_college_medicine_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_college_physics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-college_physics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_physics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_computer_security_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-computer_security|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-computer_security|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_conceptual_physics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_econometrics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-econometrics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-econometrics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_electrical_engineering_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_elementary_mathematics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_formal_logic_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_global_facts_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-global_facts|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-global_facts|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_biology_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_chemistry_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_computer_science_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_european_history_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_geography_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_government_and_politics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_macroeconomics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_mathematics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_microeconomics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_physics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_psychology_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_statistics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_us_history_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_high_school_world_history_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_human_aging_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-human_aging|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_aging|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_human_sexuality_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_international_law_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-international_law|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-international_law|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_jurisprudence_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_logical_fallacies_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_machine_learning_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_management_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-management|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-management|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_marketing_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-marketing|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-marketing|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_medical_genetics_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_miscellaneous_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_moral_disputes_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_moral_scenarios_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_nutrition_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-nutrition|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-nutrition|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_philosophy_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-philosophy|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-philosophy|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_prehistory_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-prehistory|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-prehistory|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_professional_accounting_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_professional_law_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-professional_law|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_law|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_professional_medicine_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_professional_psychology_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_public_relations_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-public_relations|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-public_relations|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_security_studies_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-security_studies|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-security_studies|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_sociology_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-sociology|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-sociology|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_us_foreign_policy_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_virology_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-virology|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-virology|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_hendrycksTest_world_religions_5 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|hendrycksTest-world_religions|5_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|hendrycksTest-world_religions|5_2023-10-03T14-29-31.026296.parquet' - config_name: harness_truthfulqa_mc_0 data_files: - split: 2023_10_03T14_29_31.026296 path: - '**/details_harness|truthfulqa:mc|0_2023-10-03T14-29-31.026296.parquet' - split: latest path: - '**/details_harness|truthfulqa:mc|0_2023-10-03T14-29-31.026296.parquet' - config_name: harness_winogrande_5 data_files: - split: 2023_10_24T02_31_53.066054 path: - '**/details_harness|winogrande|5_2023-10-24T02-31-53.066054.parquet' - split: latest path: - '**/details_harness|winogrande|5_2023-10-24T02-31-53.066054.parquet' - config_name: results data_files: - split: 2023_10_03T14_29_31.026296 path: - results_2023-10-03T14-29-31.026296.parquet - split: 2023_10_24T02_31_53.066054 path: - results_2023-10-24T02-31-53.066054.parquet - split: latest path: - results_2023-10-24T02-31-53.066054.parquet --- # Dataset Card for Evaluation run of winglian/Llama-2-3b-hf ## Dataset Description - **Homepage:** - **Repository:** https://huggingface.co/winglian/Llama-2-3b-hf - **Paper:** - **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard - **Point of Contact:** clementine@hf.co ### Dataset Summary Dataset automatically created during the evaluation run of model [winglian/Llama-2-3b-hf](https://huggingface.co/winglian/Llama-2-3b-hf) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task. The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results. An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the agregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)). To load the details from a run, you can for instance do the following: ```python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_winglian__Llama-2-3b-hf", "harness_winogrande_5", split="train") ``` ## Latest results These are the [latest results from run 2023-10-24T02:31:53.066054](https://huggingface.co/datasets/open-llm-leaderboard/details_winglian__Llama-2-3b-hf/blob/main/results_2023-10-24T02-31-53.066054.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval): ```python { "all": { "em": 0.01960989932885906, "em_stderr": 0.0014199622282460517, "f1": 0.026280411073825484, "f1_stderr": 0.0015385339771850702, "acc": 0.24822415153906865, "acc_stderr": 0.007026065573457934 }, "harness|drop|3": { "em": 0.01960989932885906, "em_stderr": 0.0014199622282460517, "f1": 0.026280411073825484, "f1_stderr": 0.0015385339771850702 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|winogrande|5": { "acc": 0.4964483030781373, "acc_stderr": 0.014052131146915867 } } ``` ### Supported Tasks and Leaderboards [More Information Needed] ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions [More Information Needed]
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集来源

该数据集是在对模型 winglian/Llama-2-3b-hf 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集结构

  • 该数据集包含 64 个配置,每个配置对应一个评估任务。
  • 数据集从 2 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_winglian__Llama-2-3b-hf", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-24T02:31:53.066054 运行的最新结果: python { "all": { "em": 0.01960989932885906, "em_stderr": 0.0014199622282460517, "f1": 0.026280411073825484, "f1_stderr": 0.0015385339771850702, "acc": 0.24822415153906865, "acc_stderr": 0.007026065573457934 }, "harness|drop|3": { "em": 0.01960989932885906, "em_stderr": 0.0014199622282460517, "f1": 0.026280411073825484, "f1_stderr": 0.0015385339771850702 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|winogrande|5": { "acc": 0.4964483030781373, "acc_stderr": 0.014052131146915867 } }

配置详情

以下是部分配置及其数据文件路径:

  • config_name: harness_arc_challenge_25

    • split: 2023_10_03T14_29_31.026296
      • path: **/details_harness|arc:challenge|25_2023-10-03T14-29-31.026296.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2023-10-03T14-29-31.026296.parquet
  • config_name: harness_drop_3

    • split: 2023_10_24T02_31_53.066054
      • path: **/details_harness|drop|3_2023-10-24T02-31-53.066054.parquet
    • split: latest
      • path: **/details_harness|drop|3_2023-10-24T02-31-53.066054.parquet
  • config_name: harness_gsm8k_5

    • split: 2023_10_24T02_31_53.066054
      • path: **/details_harness|gsm8k|5_2023-10-24T02-31-53.066054.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2023-10-24T02-31-53.066054.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_10_03T14_29_31.026296
      • path: **/details_harness|hellaswag|10_2023-10-03T14-29-31.026296.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2023-10-03T14-29-31.026296.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_10_03T14_29_31.026296
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-03T14-29-31.026296.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-03T14-29-31.026296.parquet
        • ...
    • split: latest
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-10-03T14-29-31.026296.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-10-03T14-29-31.026296.parquet
        • ...
搜集汇总
数据集介绍
main_image_url
构建方式
在大型语言模型评估领域,本数据集作为开放大语言模型排行榜的衍生成果,其构建过程体现了自动化与标准化的特点。数据集通过系统化的评估流程自动生成,记录了特定模型在多个标准化基准任务上的详细表现。评估过程涵盖64种不同的任务配置,每个配置对应一项独立的评测任务,数据源自两次独立的运行过程,每次运行的结果以时间戳命名的分割形式保存,确保了评估轨迹的完整可追溯性。
使用方法
对于研究人员而言,利用该数据集进行模型分析需借助Hugging Face的datasets库。通过指定数据集名称、具体任务配置(如“harness_winogrande_5”)以及所需的分割(如“train”指向最新结果),即可加载相应的评估细节数据。这种调用方式允许用户灵活地提取特定任务或特定时间点的评估结果,进而深入分析模型在不同能力维度上的表现,或追踪模型版本迭代过程中的性能变化趋势。
背景与挑战
背景概述
在大型语言模型(LLM)迅猛发展的背景下,模型性能的标准化评估成为推动领域进步的关键。为此,Hugging Face团队于2023年推出了Open LLM Leaderboard,旨在构建一个透明、可复现的基准测试平台。数据集“open-llm-leaderboard/details_winglian__Llama-2-3b-hf”正是该平台在评估特定模型“winglian/Llama-2-3b-hf”时自动生成的详细结果集合。它记录了模型在ARC挑战赛、DROP、GSM8K、HellaSwag以及涵盖多学科的MMLU(HendrycksTest)等64项核心任务上的表现。该数据集不仅为研究者提供了模型能力的细粒度洞察,也为社区建立了一套统一的性能比较标准,极大地促进了开源模型生态的健康发展与迭代优化。
当前挑战
该数据集致力于解决大型语言模型在多样化、复杂认知任务上的综合能力评估挑战,其核心在于如何设计一套全面且公平的基准来量化模型的推理、知识掌握与问题解决能力。在构建过程中,主要面临两大挑战:一是评估框架的整合与标准化,需要将来自不同研究团队、具有不同格式和评价指标的多个独立评测任务(如ARC、DROP等)无缝集成到一个统一的自动化流水线中,并确保评估过程的一致性与可复现性;二是数据管理与版本控制的复杂性,由于模型会进行多次评估运行,必须高效地组织和管理不同时间戳下的详细结果文件,并清晰地标识最新结果,以避免数据混淆并支持动态的性能追踪。
常用场景
经典使用场景
在大型语言模型评估领域,该数据集作为开放大语言模型排行榜的评估结果记录,其经典使用场景在于为研究人员提供模型性能的细粒度分析。通过涵盖ARC挑战、HellaSwag、Winogrande等多个基准任务,数据集允许学者深入探究模型在常识推理、语言理解及数学解题等核心认知能力上的表现,从而为模型优化与比较奠定实证基础。
解决学术问题
该数据集有效解决了大语言模型评估中标准化与可复现性的关键学术问题。通过整合多任务评估结果并记录详细配置,它为模型性能的横向对比提供了统一框架,助力研究者识别模型在特定领域的优势与局限。其意义在于推动了评估方法的透明化,促进了学术社区对模型能力边界的共识形成,为后续模型设计与训练策略的改进提供了可靠依据。
实际应用
在实际应用层面,该数据集为工业界与学术界的模型选型与部署提供了直接参考。开发者可依据评估结果筛选适合特定场景的模型,例如在需要高精度常识推理的对话系统中优先考虑Winogrande任务表现优异的模型。同时,数据集支持持续的性能追踪,帮助团队监控模型迭代效果,确保实际应用中的性能稳定与可靠。
数据集最近研究
最新研究方向
在大型语言模型评估领域,该数据集作为Open LLM Leaderboard的组成部分,聚焦于对Llama-2-3b-hf模型的多维度性能评测。前沿研究正致力于通过标准化基准任务,如ARC挑战、HellaSwag、MMLU及GSM8K等,系统量化模型在推理、常识理解与专业学科知识上的表现。随着开源模型社区的蓬勃发展,此类评估数据为模型优化与比较提供了关键依据,推动了轻量化模型在边缘计算与资源受限场景下的应用探索。其评测结果不仅反映了当前模型的能力边界,也为后续算法改进与训练策略调整指明了方向,在促进透明、可复现的AI研究生态中扮演着重要角色。
以上内容由遇见数据集搜集并总结生成
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作