kevinwang676's picture
Upload folder using huggingface_hub
be9690e verified
raw
history blame
1.2 kB
# https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.callbacks.ModelCheckpoint.html
model_checkpoint:
_target_: lightning.pytorch.callbacks.ModelCheckpoint
dirpath: ${paths.output_dir}/checkpoints # directory to save the model file
filename: checkpoint_{epoch:03d} # checkpoint filename
monitor: epoch # name of the logged metric which determines when model is improving
verbose: False # verbosity mode
save_last: true # additionally always save an exact copy of the last checkpoint to a file last.ckpt
save_top_k: 10 # save k best models (determined by above metric)
mode: "max" # "max" means higher metric value is better, can be also "min"
auto_insert_metric_name: True # when True, the checkpoints filenames will contain the metric name
save_weights_only: False # if True, then only the model’s weights will be saved
every_n_train_steps: null # number of training steps between checkpoints
train_time_interval: null # checkpoints are monitored at the specified time interval
every_n_epochs: 100 # number of epochs between checkpoints
save_on_train_epoch_end: null # whether to run checkpointing at the end of the training epoch or the end of validation