I didn’t find anything about lm_labels on T5 docs. How to explain the below code:
model = T5ForConfiditionalGeneration.from_pretrained('t5-base')
outputs = model(inputs_ids=input_ids, attention_mask=mask, decoder_input_ids=y_ids, lm_labels=lm_labels)
How to distinguish the difference between decoder_input_ids and lm_labels?