Hey, I somehow started the training but now it is taking a lot of time can you tell an approximate or another method to speed up the training?

And also can you tell me what you have put the value for LOSS_ITER it is not mentioned here so I put it the same as TRAIN_ITER i.e. 150 in word_classifier_CTC.ipynb

check the train.csv, dev.csv, and test.csv I have generated are good to use or have some error.
dataset-processed-link: https://www.kaggle.com/datasets/rahuldhanola/handwriting-dataset-processed