# How to get the result probabilities fromT5 decoding output?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-the-result-probabilities-fromt5-decoding-output%2F4718%3E%5C
**Category:** 🤗Transformers\
**Created:** [March 19, 2021, 2:41pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-the-result-probabilities-fromt5-decoding-output%2F4718 "2021-03-19T14:41:11Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Liana](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/liana/32/1315_2.png) [@Liana](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FLiana)%5C
**Post date:** [March 19, 2021, 2:41pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-the-result-probabilities-fromt5-decoding-output%2F4718%2F1 "2021-03-19T14:41:11Z")

</div>

Hello,

I am using `t5-base` to map phrases into categories, for example: “I want to eat” → “hunger”. I have hundreds of different categories, and each category may have 1-3 phrases. Therefore, this is not a classical multi-class classification task. I rather call it a text-to-text mapping task.

Is there any way to get the probability for `result` values returned for a phrase (see code snippet below)?

For example, if the phrase is “He is hungry”, the model returns top 5 most relevant labels. These results seem to be ordered by some relevance rank, so that the most relevant label is always first in `outputs` . So, my question is how can I retrieve these probabilities?

My final goal is to set a threshold on the probability, so that `outputs` would only include results that pass this threshold. If the threshold is not passed, then it should mean that nothing relevant found.

```auto
t5_tokenizer = T5Tokenizer.from_pretrained('t5-base')
t5_model = T5ForConditionalGeneration.from_pretrained('t5-base')
...
model.model.eval()
outputs = model.model.generate(
    input_ids=test_input_ids,attention_mask=test_attention_mask,
    max_length=64,
    early_stopping=True,
    num_beams=10,
    num_return_sequences=5,
    no_repeat_ngram_size=2
)

for output in outputs:
    result = t5_tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
    print(result)

```

---

<div class="post-metadata">

**Author:** ![tanjiro817](https://avatars.discourse-cdn.com/v4/letter/t/bc79bd/32.png) [@tanjiro817](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ftanjiro817)%5C
**Post date:** [October 30, 2022, 9:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-get-the-result-probabilities-fromt5-decoding-output%2F4718%2F2 "2022-10-30T21:55:18Z")

</div>

Hi Liana, did you figure out how to do this?