| python run_hybrid_clip.py \ | |
| --output_dir "./" \ | |
| --text_model_name_or_path="roberta-base" \ | |
| --vision_model_name_or_path="openai/clip-vit-base-patch32" \ | |
| --tokenizer_name="roberta-base" \ | |
| --train_file="../coco_dataset/train_dataset.json" \ | |
| --validation_file="../coco_dataset/valid_dataset.json" \ | |
| --do_train --do_eval \ | |
| --num_train_epochs="40" --max_seq_length 96 \ | |
| --per_device_train_batch_size="64" \ | |
| --per_device_eval_batch_size="64" \ | |
| --learning_rate="5e-5" --warmup_steps="0" --weight_decay 0.1 \ | |
| --overwrite_output_dir \ | |
| --preprocessing_num_workers 32 \ | |
| --push_to_hub | |