hi, plz help me
Hello, I am a college student who is conducting a voice classification study. I am currently working on fin-tuning of the ast model. But there's a problem, and the dataset I have is not learning properly. The problem is trainer.train(), but I wonder what the shape of the dataset of train_dataset in trainer.train() is when fine tuning. Could you please share some things that I can help you with, such as sharing or advice?
The error message I currently have is as follows. RuntimeError: expected scalar type Long but found Int. Please let me know if there are any mistakes. I'll fix it Thank you.
https://drive.google.com/file/d/1vHYEIlXl3X2QCPS0eLSD0NX8kg3E6IFu/view?usp=sharing
Hi! I'm an enthusiast in deep learning, so I can't give many advices, because I don't know how some things work :)
But I see that your data type is different from model pipeline is expected.
Maybe you should try to train model pipeline on other dataset, like "marsyas/gtzan". If pipeline will be work good that your dataset format isn't good for pipeline.
Also, you didn't attach a link to dataset and I can't see which format dataset contain.
And that I saw you have problem with to compute loss function:
611 elif self.config.problem_type == "single_label_classification":
612 loss_fct = CrossEntropyLoss()
--> 613 loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
Try to find how to fix this problem