pyFDN.TrainLog#

class pyFDN.TrainLog(train_loss=<factory>, loss_log=<factory>, steps_run=0, stopped_early=False)[source]#

Per-step loss history and stopping info from a training run.

train_loss#

Total loss at each step.

Type:

list of float

loss_log#

Per-criterion loss history, keyed by criterion class name.

Type:

dict of str to list of float

steps_run#

Steps actually run.

Type:

int

stopped_early#

Whether a plateau stopped it before max_steps.

Type:

bool

__init__(train_loss=<factory>, loss_log=<factory>, steps_run=0, stopped_early=False)#

Methods

__init__([train_loss, loss_log, steps_run, ...])

Attributes

steps_run

stopped_early

train_loss

loss_log

loss_log: dict[str, list[float]]#
steps_run: int = 0#
stopped_early: bool = False#
train_loss: list[float]#