default.yaml

# rich_progress_bar:
#   _target_: pytorch_lightning.callbacks.RichProgressBar

rich_model_summary:
  _target_: pytorch_lightning.callbacks.RichModelSummary

model_checkpoint:
  _target_: pytorch_lightning.callbacks.ModelCheckpoint
  monitor: "val/acc" # name of the logged metric which determines when model is improving
  mode: "max" # can be "max" or "min"
  save_top_k: 1 # save k best models (determined by above metric)
  save_last: True # additionaly always save model from last epoch
  verbose: False
  dirpath: ${oc.env:CHECKPOINT_DIR,checkpoints}/${oc.select:name,''}
  filename: "epoch_{epoch:03d}"
  auto_insert_metric_name: False

early_stopping:
  _target_: pytorch_lightning.callbacks.EarlyStopping
  monitor: "val/acc" # name of the logged metric which determines when model is improving
  mode: "max" # can be "max" or "min"
  patience: 100 # how many epochs of not improving until training stops
  min_delta: 0 # minimum change in the monitored metric needed to qualify as an improvement

learning_rate_monitor:
  _target_: pytorch_lightning.callbacks.LearningRateMonitor
  logging_interval: step

speed_monitor:
  _target_: src.callbacks.speed_monitor.SpeedMonitor
  intra_step_time: True
  inter_step_time: True
  epoch_time: True

loss_scale_monitor:
  _target_: src.callbacks.loss_scale_monitor.LossScaleMonitor

params_log:
  _target_: src.callbacks.params_log.ParamsLog
  total_params_log: True
  trainable_params_log: True
  non_trainable_params_log: True

gpu_affinity:
  _target_: src.callbacks.gpu_affinity.GpuAffinity