# FineTune TFT5ForConditionalGeneration Batch Size

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-tft5forconditionalgeneration-batch-size%2F24855%3E%5C
**Category:** Models\
**Created:** [October 23, 2022, 10:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-tft5forconditionalgeneration-batch-size%2F24855 "2022-10-23T22:25:16Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![RERobbins](https://avatars.discourse-cdn.com/v4/letter/r/22d042/32.png) [@RERobbins](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FRERobbins)%5C
**Post date:** [October 23, 2022, 10:25pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffinetune-tft5forconditionalgeneration-batch-size%2F24855%2F1 "2022-10-23T22:25:16Z")

</div>

How do I set the batch size when trying to FineTune a TFT5ForConditionalGeneration model?

Currently, I’ve run my input sequences and labels through the T5Tokenizer and am calling the model with…

output = model(input\_ids=input\_ids, attention\_mask=attention\_mask, labels=target\_ids)

where model = TFT5ForConditionalGeneration.from\_pretrained(“google/t5-v1\_1-base”)