resume_from_checkpoint_path: null result_path: "./result" pretrained_model_name_or_path: "naver-clova-ix/donut-base" dataset_name_or_paths: ["./dataset/zhtrainticket"] # should be prepared from https://github.com/beacandler/EATEN sort_json_key: True train_batch_sizes: [8] val_batch_sizes: [1] input_size: [960, 1280] max_length: 256 align_long_axis: False num_nodes: 1 seed: 2022 lr: 3e-5 warmup_steps: 300 num_training_samples_per_epoch: 1368 max_epochs: 10 max_steps: -1 num_workers: 8 val_check_interval: 1.0 check_val_every_n_epoch: 1 gradient_clip_val: 1.0 verbose: True