_target_: lightning.pytorch.trainer.Trainer
default_root_dir: ${paths.output_dir}

# set True to to ensure deterministic results
# makes training slower but gives more reproducibility than just setting seeds
deterministic: False

accelerator: gpu
devices: auto
strategy: 
  _target_: lightning.pytorch.strategies.DDPStrategy
  find_unused_parameters: True
  gradient_as_bucket_view: True
  timeout:
    _target_: datetime.timedelta
    seconds: 1800 # 30 minutes timeout for each training step
num_nodes: 1
min_epochs: 1 # prevents early stopping
max_steps: 100000
precision: bf16-mixed
val_check_interval: 5000
check_val_every_n_epoch: null
num_sanity_val_steps: 0
limit_val_batches: 0.0