Larger models learn slowly?

[chenwydj]

Dear authors,

Thank you very much for this great repo!

I am training larger models (T2T-ViT-19/24, etc.), and I find during training their accuracies increase slower than small models like T2T-ViT-7. Is this an expected behavior?

Thank you!

[yuanli2333]

Hi, large model would converge slower at first 10 to 20 epochs, but will increase faster after the initial stage.

[chenwydj]

Thank you!