python run_image_classification.py \ | |
--train_dir /trunk/shared/eebo_data/images_cropped/ \ | |
--validation_dir /trunk/shared/eebo_data/images_cropped/ \ | |
--output_dir ./microsoft_dit_lr_1e-3/ \ | |
--remove_unused_columns False \ | |
--label_column_name labels \ | |
--do_train \ | |
--do_eval \ | |
--push_to_hub \ | |
--push_to_hub_model_id donut-base-beans \ | |
--learning_rate 1e-3 \ | |
--num_train_epochs 5 \ | |
--per_device_train_batch_size 8 \ | |
--per_device_eval_batch_size 8 \ | |
--logging_strategy steps \ | |
--logging_steps 10 \ | |
--eval_strategy epoch \ | |
--save_strategy epoch \ | |
--load_best_model_at_end True \ | |
--save_total_limit 5 \ | |
--seed 1337 \ | |
--ignore_mismatched_sizes \ | |
--image_column_name image_url \ | |
--label_column_name label \ | |
--model_name_or_path microsoft/dit-base-finetuned-rvlcdip |