Training Hugging face model

Hello, I am using the Sagemaker Jumpstart Flan-T5 XL model to create a LLM Chatbot. I have completed the step by step and additional advanced examples to deploy an untrained model. Now I would like to train the model to do simple word problems.

I would like to train it using this gsm8k data set.
I have not seen any good documentation and I am hoping somebody can point me to a guide (preferably step by step) to use the data set above and place it in the right format, etc.

Thank you.