python run_hybrid_clip.py \
    --output_dir "./output_141230_training_examples" \
    --text_model_name_or_path="bertin-project/bertin-roberta-base-spanish" \
    --vision_model_name_or_path="openai/clip-vit-base-patch32" \
    --tokenizer_name="bertin-project/bertin-roberta-base-spanish" \
    --train_file="/home/${USER}/data/wit_scale_converted/train_dataset_scale_converted_98_1_1_split.json" \
    --validation_file="/home/${USER}/data/wit_scale_converted/valid_dataset_scale_converted_98_1_1_split.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