donut-booking-gradio / config /train_docvqa.yaml
uartimcs's picture
Upload folder using huggingface_hub
608a96e verified
raw
history blame
647 Bytes
resume_from_checkpoint_path: null
result_path: "./result"
pretrained_model_name_or_path: "naver-clova-ix/donut-base"
dataset_name_or_paths: ["./dataset/docvqa"] # should be prepared from https://rrc.cvc.uab.es/?ch=17
sort_json_key: True
train_batch_sizes: [2]
val_batch_sizes: [4]
input_size: [2560, 1920]
max_length: 128
align_long_axis: False
# num_nodes: 8 # memo: donut-base-finetuned-docvqa was trained with 8 nodes
num_nodes: 1
seed: 2022
lr: 3e-5
warmup_steps: 10000
num_training_samples_per_epoch: 39463
max_epochs: 300
max_steps: -1
num_workers: 8
val_check_interval: 1.0
check_val_every_n_epoch: 1
gradient_clip_val: 0.25
verbose: True