config.yaml

resume_from_checkpoint_path: None
result_path: 'trainer/result'
pretrained_model_name_or_path: 'marzanconsulting/donut-dr-matriculas-ocr'
dataset_name_or_paths: 
  - 'trainer/dataset'
task_start_tokens: 
  - '<s_matricula>'
sort_json_key: False
train_batch_sizes: 
  - 5
val_batch_sizes: 
  - 1
input_size: 
  - 960
  - 1280
max_length: 868
max_position_embeddings: 868
align_long_axis: False
num_nodes: 1
seed: 2022
lr: 3e-05
warmup_steps: 300
num_training_samples_per_epoch: 800
max_epochs: 50
max_steps: -1
num_workers: 12
val_check_interval: 1.0
check_val_every_n_epoch: 3
gradient_clip_val: 1.0
verbose: True
model_dir: ''
tensorboard_dir: ''
checkpoint_dir: 
exp_name: 'train_cord_matriculas'
exp_version: 'mmc_v1'