In this Notebook you will learn how to transformer based large language model on your own dataset
-
preprocess a text dataset
- Load dataset
- Analyze features and target
- Tokenize text
- add padding to make same length
- Convert Dict to Tensorflow dataset for trainable keras model
-
Optimize the model
- You will learn how to optimize the model hyperparameters
-
Train model on your own prepared dataset
-
Evaluate your trained model
- You will learn how to evaluate model 'accuracy' and 'f1' score