Thank you for your excellent work. I noticed that the model with the highest accuracy on the "val_dataset" during the training phase is used as the initial model for the fine-tuning phase，and the testing is also based on this same "val_dataset". I am unsure if this is an acceptable practice during training, and I would appreciate your guidance. Thank you again.
Thank you for your excellent work. I noticed that the model with the highest accuracy on the "val_dataset" during the training phase is used as the initial model for the fine-tuning phase，and the testing is also based on this same "val_dataset". I am unsure if this is an acceptable practice during training, and I would appreciate your guidance. Thank you again.