Hi. I'm following the steps on Train a model on your sequence and reached step 7, but it is running like forever. It has been over 83k steps in pretraining and it's still on-going:
I think they use the same number of iterations for both blended model training and static only pretraining. It's specified by N_iters and defaults to 300001 in your case.
Hi. I'm following the steps on Train a model on your sequence and reached step 7, but it is running like forever. It has been over 83k steps in pretraining and it's still on-going: