./run_t5_mlm_flax_streaming.py\
    --model_name_or_path="./" \
    --output_dir="./" \
    --config_name="./" \
    --tokenizer_name="./" \
    --dataset_name="pere/nb_nn_balanced_shuffled" \
    --max_seq_length="512" \
    --per_device_train_batch_size="32" \
    --per_device_eval_batch_size="32" \
    --learning_rate="0.005" \
    --weight_decay="0.001" \
    --warmup_steps="2000" \
    --overwrite_output_dir \
    --logging_steps="500" \
    --save_steps="2500" \
    --eval_steps="2500"\
    --push_to_hub \
    --preprocessing_num_workers 96 \
    --adafactor