Which benchmark is implemented, e.g. image classification
Ideally, a list of command lines
Ideally, a list of command lines
Ideally, a list of command lines
Cite paper describing dataset plus any additional attribution requested by dataset authors
What preprocessing is done to the the dataset?
How is the test set extracted?
In what order is the training data traversed?
In what order is the test data traversed?
Describe simulation environment briefly, if applicable.
Cite paper describing model plus any additional attribution requested by code authors
Brief summary of structure of model
How are weights and biases initialized
Name/description of loss function used
Name of optimizer used
What is the target quality metric
What is the numeric quality target
How many training items between quality evaluations (typically all, evaluated every epoch)
How many test items per quality evaluation (typically all)