Hi there, thank you for sharing this impressive work. I was briefly looking through the training configuration and became curious about the computational cost. I was wondering if you could share some details regarding how many epochs are typically needed for the model to converge?
Hi there, thank you for sharing this impressive work. I was briefly looking through the training configuration and became curious about the computational cost. I was wondering if you could share some details regarding how many epochs are typically needed for the model to converge?