model.md

Model

Link to code

The Model metadata schema is an extension of the Processing schema tailored to model weights and other data and code artifacts underlying machine learning models - these may be trained on one dataset and evaluated on others, and may be intended to undergo further training iteratively in future versions.

Thus new evaluations and training steps can easily be appended for new model versions. This metadata should be documented for any models that see widespread internal use or public release, in order to facilitate model reuse and document provenance.

Core file

Model

Description of a machine learning model including architecture, training, and evaluation details

Field	Type	Title (Description)
name	str	Name
version	str	Version
example_run_code	Code	Example run code (Code to run the model, possibly including example parameters/data)
architecture	ModelArchitecture	architecture (Model architecture / type of model)
software_framework	Optional[Software]	Software framework
architecture_parameters	Optional[dict]	Architecture parameters (Parameters of model architecture, such as input signature or number of layers.)
intended_use	str	Intended model use (Semantic description of intended use)
limitations	Optional[str]	Model limitations
training	List[ModelTraining or ModelPretraining]	Training
evaluations	List[ModelEvaluation]	Evaluations
notes	Optional[str]	Notes

Model definitions

ModelEvaluation

Description of model evaluation

Field	Type	Title (Description)
process_type	ProcessName
performance	List[PerformanceMetric]	Evaluation performance
name	str	Name (('Unique name of the processing step.', ' If not provided, the type will be used as the name.'))
stage	ProcessStage	Processing stage
code	Code	Code (Code used for processing)
experimenters	List[str]	Experimenters (People responsible for processing)
pipeline_name	Optional[str]	Pipeline name (Pipeline names must exist in Processing.pipelines)
start_date_time	datetime (timezone-aware)	Start date time
end_date_time	Optional[datetime (timezone-aware)]	End date time
output_path	Optional[List[AssetPath]]	Output path (Path to processing outputs, if stored.)
output_parameters	Optional[dict]	Outputs (Output parameters)
notes	Optional[str]	Notes
resources	Optional[ResourceUsage]	Process resource usage

ModelPretraining

Description of model pretraining

Field	Type	Title (Description)
source_url	str	Pretrained source URL (URL for pretrained weights)

ModelTraining

Description of model training

Field	Type	Title (Description)
process_type	ProcessName
train_performance	List[PerformanceMetric]	Training performance (Performance on training set)
test_performance	Optional[List[PerformanceMetric]]	Test performance (Performance on test data, evaluated during training)
test_evaluation_method	Optional[str]	Test evaluation method (Approach to cross-validation or Train/test splitting)
name	str	Name (('Unique name of the processing step.', ' If not provided, the type will be used as the name.'))
stage	ProcessStage	Processing stage
code	Code	Code (Code used for processing)
experimenters	List[str]	Experimenters (People responsible for processing)
pipeline_name	Optional[str]	Pipeline name (Pipeline names must exist in Processing.pipelines)
start_date_time	datetime (timezone-aware)	Start date time
end_date_time	Optional[datetime (timezone-aware)]	End date time
output_path	Optional[List[AssetPath]]	Output path (Path to processing outputs, if stored.)
output_parameters	Optional[dict]	Outputs (Output parameters)
notes	Optional[str]	Notes
resources	Optional[ResourceUsage]	Process resource usage

PerformanceMetric

Description of a performance metric

Field	Type	Title (Description)
name	str	Metric name
value	typing.Any	Metric value