open-llm-leaderboard-old/details_openchat__openchat_v2_w
收藏Hugging Face2023-10-25 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_openchat__openchat_v2_w
下载链接
链接失效反馈官方服务:
资源简介:
---
pretty_name: Evaluation run of openchat/openchat_v2_w
dataset_summary: "Dataset automatically created during the evaluation run of model\
\ [openchat/openchat_v2_w](https://huggingface.co/openchat/openchat_v2_w) 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 4 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_openchat__openchat_v2_w\"\
,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\
These are the [latest results from run 2023-10-25T10:16:39.894095](https://huggingface.co/datasets/open-llm-leaderboard/details_openchat__openchat_v2_w/blob/main/results_2023-10-25T10-16-39.894095.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\": 0.0017827181208053692,\n\
\ \"em_stderr\": 0.0004320097346038692,\n \"f1\": 0.06345113255033595,\n\
\ \"f1_stderr\": 0.0013770461350277562,\n \"acc\": 0.4217142689595871,\n\
\ \"acc_stderr\": 0.009831291629413687\n },\n \"harness|drop|3\": {\n\
\ \"em\": 0.0017827181208053692,\n \"em_stderr\": 0.0004320097346038692,\n\
\ \"f1\": 0.06345113255033595,\n \"f1_stderr\": 0.0013770461350277562\n\
\ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.0841546626231994,\n \
\ \"acc_stderr\": 0.007647024046603207\n },\n \"harness|winogrande|5\"\
: {\n \"acc\": 0.7592738752959748,\n \"acc_stderr\": 0.012015559212224167\n\
\ }\n}\n```"
repo_url: https://huggingface.co/openchat/openchat_v2_w
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_07_24T16_07_10.180940
path:
- '**/details_harness|arc:challenge|25_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|arc:challenge|25_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|arc:challenge|25_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_drop_3
data_files:
- split: 2023_10_19T04_55_59.182634
path:
- '**/details_harness|drop|3_2023-10-19T04-55-59.182634.parquet'
- split: 2023_10_25T10_16_39.894095
path:
- '**/details_harness|drop|3_2023-10-25T10-16-39.894095.parquet'
- split: latest
path:
- '**/details_harness|drop|3_2023-10-25T10-16-39.894095.parquet'
- config_name: harness_gsm8k_5
data_files:
- split: 2023_10_19T04_55_59.182634
path:
- '**/details_harness|gsm8k|5_2023-10-19T04-55-59.182634.parquet'
- split: 2023_10_25T10_16_39.894095
path:
- '**/details_harness|gsm8k|5_2023-10-25T10-16-39.894095.parquet'
- split: latest
path:
- '**/details_harness|gsm8k|5_2023-10-25T10-16-39.894095.parquet'
- config_name: harness_hellaswag_10
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hellaswag|10_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hellaswag|10_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hellaswag|10_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-07-24T16:07:10.180940.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-09T10:10:49.498602.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_abstract_algebra_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_anatomy_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_astronomy_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_business_ethics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_clinical_knowledge_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_college_biology_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_college_chemistry_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_college_computer_science_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_college_mathematics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_college_medicine_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_college_physics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_computer_security_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_conceptual_physics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_econometrics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_electrical_engineering_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_elementary_mathematics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_formal_logic_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_global_facts_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_biology_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_chemistry_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_computer_science_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_european_history_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_geography_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_government_and_politics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_macroeconomics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_mathematics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_microeconomics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_physics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_psychology_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_statistics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_us_history_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_high_school_world_history_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_human_aging_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_human_sexuality_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_international_law_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_jurisprudence_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_logical_fallacies_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_machine_learning_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_management_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-management|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_marketing_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_medical_genetics_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_miscellaneous_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_moral_disputes_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_moral_scenarios_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_nutrition_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_philosophy_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_prehistory_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_professional_accounting_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_professional_law_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_professional_medicine_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_professional_psychology_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_public_relations_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_security_studies_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_sociology_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_us_foreign_policy_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_virology_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-virology|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_hendrycksTest_world_religions_5
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_truthfulqa_mc_0
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- '**/details_harness|truthfulqa:mc|0_2023-07-24T16:07:10.180940.parquet'
- split: 2023_08_09T10_10_49.498602
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-09T10:10:49.498602.parquet'
- split: latest
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-09T10:10:49.498602.parquet'
- config_name: harness_winogrande_5
data_files:
- split: 2023_10_19T04_55_59.182634
path:
- '**/details_harness|winogrande|5_2023-10-19T04-55-59.182634.parquet'
- split: 2023_10_25T10_16_39.894095
path:
- '**/details_harness|winogrande|5_2023-10-25T10-16-39.894095.parquet'
- split: latest
path:
- '**/details_harness|winogrande|5_2023-10-25T10-16-39.894095.parquet'
- config_name: results
data_files:
- split: 2023_07_24T16_07_10.180940
path:
- results_2023-07-24T16:07:10.180940.parquet
- split: 2023_08_09T10_10_49.498602
path:
- results_2023-08-09T10:10:49.498602.parquet
- split: 2023_10_19T04_55_59.182634
path:
- results_2023-10-19T04-55-59.182634.parquet
- split: 2023_10_25T10_16_39.894095
path:
- results_2023-10-25T10-16-39.894095.parquet
- split: latest
path:
- results_2023-10-25T10-16-39.894095.parquet
---
# Dataset Card for Evaluation run of openchat/openchat_v2_w
## Dataset Description
- **Homepage:**
- **Repository:** https://huggingface.co/openchat/openchat_v2_w
- **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 [openchat/openchat_v2_w](https://huggingface.co/openchat/openchat_v2_w) 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 4 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_openchat__openchat_v2_w",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-10-25T10:16:39.894095](https://huggingface.co/datasets/open-llm-leaderboard/details_openchat__openchat_v2_w/blob/main/results_2023-10-25T10-16-39.894095.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": 0.0017827181208053692,
"em_stderr": 0.0004320097346038692,
"f1": 0.06345113255033595,
"f1_stderr": 0.0013770461350277562,
"acc": 0.4217142689595871,
"acc_stderr": 0.009831291629413687
},
"harness|drop|3": {
"em": 0.0017827181208053692,
"em_stderr": 0.0004320097346038692,
"f1": 0.06345113255033595,
"f1_stderr": 0.0013770461350277562
},
"harness|gsm8k|5": {
"acc": 0.0841546626231994,
"acc_stderr": 0.007647024046603207
},
"harness|winogrande|5": {
"acc": 0.7592738752959748,
"acc_stderr": 0.012015559212224167
}
}
```
### 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]
原始信息汇总
数据集概述
数据集名称
- 名称: Evaluation run of openchat/openchat_v2_w
数据集描述
- 描述: 该数据集是在对模型 openchat/openchat_v2_w 进行评估运行期间自动创建的,用于 Open LLM Leaderboard。
数据集组成
- 组成: 数据集包含 64 个配置,每个配置对应一个评估任务。
- 创建: 数据集从 4 次运行中创建,每次运行在每个配置中作为一个特定的分割存在,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
- 结果配置: 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
- 加载示例: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_openchat__openchat_v2_w", "harness_winogrande_5", split="train")
最新结果
- 最新结果: 这些是最新结果,来自 2023-10-25T10:16:39.894095 的运行。 python { "all": { "em": 0.0017827181208053692, "em_stderr": 0.0004320097346038692, "f1": 0.06345113255033595, "f1_stderr": 0.0013770461350277562, "acc": 0.4217142689595871, "acc_stderr": 0.009831291629413687 }, "harness|drop|3": { "em": 0.0017827181208053692, "em_stderr": 0.0004320097346038692, "f1": 0.06345113255033595, "f1_stderr": 0.0013770461350277562 }, "harness|gsm8k|5": { "acc": 0.0841546626231994, "acc_stderr": 0.007647024046603207 }, "harness|winogrande|5": { "acc": 0.7592738752959748, "acc_stderr": 0.012015559212224167 } }
配置详情
-
配置名称: harness_arc_challenge_25
- 分割: 2023_07_24T16_07_10.180940
- 路径: **/details_harness|arc:challenge|25_2023-07-24T16:07:10.180940.parquet
- 分割: 2023_08_09T10_10_49.498602
- 路径: **/details_harness|arc:challenge|25_2023-08-09T10:10:49.498602.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2023-08-09T10:10:49.498602.parquet
- 分割: 2023_07_24T16_07_10.180940
-
配置名称: harness_drop_3
- 分割: 2023_10_19T04_55_59.182634
- 路径: **/details_harness|drop|3_2023-10-19T04-55-59.182634.parquet
- 分割: 2023_10_25T10_16_39.894095
- 路径: **/details_harness|drop|3_2023-10-25T10-16-39.894095.parquet
- 分割: latest
- 路径: **/details_harness|drop|3_2023-10-25T10-16-39.894095.parquet
- 分割: 2023_10_19T04_55_59.182634
-
配置名称: harness_gsm8k_5
- 分割: 2023_10_19T04_55_59.182634
- 路径: **/details_harness|gsm8k|5_2023-10-19T04-55-59.182634.parquet
- 分割: 2023_10_25T10_16_39.894095
- 路径: **/details_harness|gsm8k|5_2023-10-25T10-16-39.894095.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2023-10-25T10-16-39.894095.parquet
- 分割: 2023_10_19T04_55_59.182634
-
配置名称: harness_hellaswag_10
- 分割: 2023_07_24T16_07_10.180940
- 路径: **/details_harness|hellaswag|10_2023-07-24T16:07:10.180940.parquet
- 分割: 2023_08_09T10_10_49.498602
- 路径: **/details_harness|hellaswag|10_2023-08-09T10:10:49.498602.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2023-08-09T10:10:49.498602.parquet
- 分割: 2023_07_24T16_07_10.180940
-
配置名称: harness_hendrycksTest_5
- 分割: 2023_07_24T16_07_10.180940
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-anatomy|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-astronomy|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-college_biology|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-college_physics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-computer_security|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-econometrics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-global_facts|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-human_aging|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-international_law|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-management|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-marketing|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2023-07-24T16:07:10.180940.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2023-07-24T16:07:10.1
- 路径:
- 分割: 2023_07_24T16_07_10.180940
搜集汇总
数据集介绍

构建方式
本数据集源自Open LLM Leaderboard对模型openchat/openchat_v2_w的自动化评估流程,旨在系统记录模型在多项基准任务上的细粒度表现。数据集构建过程中,针对每个评估任务(如ARC挑战集、DROP、GSM8K、HellaSwag及MMLU等)均设立了独立配置,共计64项。每次完整评估运行的结果被存储为一个独立的数据分割,并以该次运行的时间戳命名,而“train”分割则始终指向最新一次的评估数据。此外,一个名为“results”的专属配置汇总了所有运行轮次的聚合指标,用于在Leaderboard上计算与展示整体性能。数据以Parquet格式存储,确保了高效读写与结构化存储的便捷性。
特点
该数据集的核心特色在于其精细化的任务划分与时间序列追踪能力。它覆盖了从常识推理(如ARC、HellaSwag)、数学问题求解(GSM8K)到复杂文本理解(DROP)和多领域知识问答(MMLU)等多样化的自然语言处理挑战,能够全面反映模型在不同能力维度上的表现。通过为每次评估运行独立保存分割,研究者得以追溯模型性能的历时变化,分析不同训练阶段或版本间的演进轨迹。同时,数据集的“train”分割自动指向最新结果,为持续监控模型状态提供了便捷的接口。聚合配置“results”则提供了宏观视角,便于快速对比模型在各类任务上的综合水准。
使用方法
使用该数据集时,研究者可通过Hugging Face的datasets库进行加载。例如,通过指定数据集名称、任务配置(如“harness_winogrande_5”)及所需分割(如“train”),即可获取对应任务最新评估的详细结果。若需回溯历史数据,则可用具体时间戳分割名替代“train”。加载后的数据可直接用于分析模型在特定任务上的预测细节、计算置信区间或进行误差分析。此外,借助“results”配置,用户能便捷地获取所有任务聚合后的评估指标,从而支持跨模型的性能对比或生成可视化报告。
背景与挑战
背景概述
在大型语言模型迅猛发展的浪潮中,如何系统性地评估其多维度能力成为学界与工业界共同关注的焦点。Open LLM Leaderboard应运而生,由Hugging Face团队于2023年主导创建,旨在为开源大语言模型提供标准化、透明化的性能对比平台。该数据集记录了openchat/openchat_v2_w模型在多个基准任务上的评估结果,涵盖ARC-Challenge、DROP、GSM8K、HellaSwag及涵盖57个学科的MMLU等核心测试集,其核心研究问题在于通过细粒度的任务分解,揭示模型在常识推理、数学逻辑、文本理解等不同维度的表现差异。该数据集不仅为OpenChat系列模型的迭代提供了关键参考,更推动了整个开源社区对模型评估规范化的思考,成为衡量开源语言模型进展的重要标尺。
当前挑战
该数据集所面临的挑战首先体现在领域层面:大语言模型的评估任务日趋复杂,单一基准难以全面反映模型能力,而多任务评估又面临任务间评分权重与解释性难题,例如DROP数据集对数值推理与精确匹配的高要求与GSM8K的数学推理任务存在本质差异,使得综合排名难以精准指导实际应用场景。构建过程中亦遭遇技术瓶颈:评估结果需通过多次运行(如该数据集记录了4次独立评估)以确保统计稳健性,但不同时间戳的运行结果可能因模型版本更新或环境变动而产生偏差;同时,数据存储格式采用Parquet与多配置分片设计,虽提升了查询效率,却对数据加载与跨任务联合分析的工程实现提出了更高要求。
常用场景
经典使用场景
在大规模语言模型评测领域,Open LLM Leaderboard的细节数据集扮演着不可或缺的角色。该数据集专为记录模型openchat/openchat_v2_w在多个标准化任务上的评估结果而设计,涵盖ARC挑战、HellaSwag、MMLU、TruthfulQA等经典基准。研究者可借助此数据集,系统性地剖析模型在常识推理、知识问答、数学求解及文本理解等维度的表现,从而构建横向对比的基准框架。其精细化的配置结构,允许按任务和时间戳分片加载,为复现实验与深入分析提供了坚实的数据基础。
衍生相关工作
此数据集衍生了一系列围绕大语言模型评测标准化与自动化的重要工作。其结构设计启发了后续多个开源评测框架,如LM Evaluation Harness的集成与扩展,使得新模型能够无缝接入统一的评估流水线。此外,基于该数据集的时间戳分片特性,研究者得以追踪模型性能随训练迭代的演变轨迹,催生了关于模型收敛性与鲁棒性的深入分析。这些工作进一步巩固了Open LLM Leaderboard作为社区公认的模型能力度量基准的地位。
数据集最近研究
最新研究方向
在大型语言模型(LLM)评估领域,Open LLM Leaderboard已成为衡量模型综合能力的重要基准平台。该数据集记录了openchat_v2_w模型在多个关键任务上的评测结果,涵盖了从常识推理(如ARC Challenge、HellaSwag)到数学推理(GSM8K)再到阅读理解(DROP)等多样化维度。当前前沿研究方向聚焦于如何通过细粒度、多任务评估体系揭示模型在不同认知层面的真实能力边界,特别是在零样本泛化与鲁棒性方面。该数据集的发布不仅为OpenChat系列模型的迭代优化提供了可量化的性能指标,更推动了开源社区对LLM评估标准化与透明化的深入探索。其包含的多轮次评测结果(如2023年10月的更新)反映了模型在持续改进过程中的动态表现,为理解模型学习规律和评估偏差提供了宝贵数据支撑,对构建更公正、全面的LLM评估框架具有重要参考价值。
以上内容由遇见数据集搜集并总结生成



