So I’m trying to fine tune ResNet50, but i’m new doing that, so I’m trying with a binary classification, but I’m not sure if I’m setting it correctly, because my accuracy at the end is weird, apparently the epochs reach 0,8, but when I’m testing it is very low, here’s my code:

ValueError: Asking to pad but the tokenizer does not have a padding token. Please select a token to use as pad_token (tokenizer.pad_token = tokenizer.eos_token e.g.) or add a new pad token via tokenizer.add_special_tokens({'pad_token': '[PAD]'}).