install pytorch 
install transformers from source: pip install git+https://github.com/huggingface/transformers
instal datasets: pip install datasets
install tokenizers: pip install tokenizers

to run: go do a solution directory and: bash run.sh


adjust:
per_device_train_batch_size
per_device_eval_batch_size
gradient_accumulation_steps

if you want to run scripts on other dataset remeber to adjust max_seq_length