Training Hugging face model

Question

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](https://huggingface.co/datasets/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.

Giovanni Lauria · Answer

You can find a detailed example notebook in the amazon-sagemaker-examples GitHub repository. This notebook demonstrates how to build, train, and deploy FLAN T5 models using Amazon SageMaker.

https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart-foundation-models/text2text-generation-flan-t5.ipynb

Training Hugging face model

Add your answer

Relevant content