Hi, at training, I’m using the forward pass and batch_decode on the logits to get the decoded output: outputs = model( input_ids, attention_mask, dec_input_ids, dec_attention_mask, labels=dec_input_ids, ) loss, logits = outputs.loss, outputs.logi…

T5 forward pass versus generate, latter outputs non-sense

deathcrush March 25, 2021, 1:06pm 9

I happened to stumble across this post, which has a similar flavour to your error. Have a look!

Topic		Replies	Views
T5 Model Generate and Model Outputs Vastly Different Beginners	1	757	September 11, 2022
T5 - model.generate() issue Beginners	2	674	March 18, 2024
Untrained T5 model outputting logits that argmax to the decoder_input_ids Beginners	0	495	September 28, 2022
The output of T5 is not consistent on multiple sequences 🤗Transformers	1	847	May 11, 2022
Extracting Logits From T5 Output Beginners	5	2003	January 9, 2024