123lcy123
123lcy123
Sorry, my description was not clear, I mean "type in an arbitrary query phrase like made of metal (material), where can I cook? (activity), festive (abstract concept) etc" in code...
I have the same problem, have you solved it?
When fine-tuning CogVideoX-5B on my own dataset, I've also encountered the same problem where the loss is noisy and doesn't go down. Have you discovered what the issue might be?
The batch_size is 32.