[mock_model]
requires_grad = true
use_activation = true

[clock]
verbose = false

[gradient_clipping]
clip_grad_norm = 1.0

[training]
duration = "100:epoch"
seed = 0
device = "cpu"
dtype = "float32"
batch_size = 4
gradient_accumulation = "4:step"
evaluation_interval = "5:epoch"
evaluation_seed = 1

[optimizer]
optimizer = "SGD"
learning_rate = 1

[scheduler]
scheduler_type = "ConstantLR"
update_interval = "1:step"
warmup = "20:step"