# Fine-tune summarization never works well

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tune-summarization-never-works-well%2F74723%3E%5C
**Category:** Beginners\
**Created:** [February 25, 2024, 6:41pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tune-summarization-never-works-well%2F74723 "2024-02-25T18:41:52Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![shahadalll](https://avatars.discourse-cdn.com/v4/letter/s/ebca7d/32.png) [@shahadalll](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fshahadalll)%5C
**Post date:** [February 25, 2024, 6:41pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tune-summarization-never-works-well%2F74723%2F1 "2024-02-25T18:41:52Z")

</div>

Hello, guys. I hope you are all good.

I am a beginner to Hugging Face, and I am trying to fine-tune a model for a summarization task.

I tried bert-multilingual-cased and mT5, but I have the same problem with both of them: the summary does not exceed about 11 words, and they are not good summaries.

I used the SAMSum conversational dataset translated into Arabic. I do not know how to solve this problem! I thought by specifying  
`max_input_length = 1024` and `max_target_length = 128`, I would guarantee it works, but it does not, and I cannot figure out where the problem is. You can find the code (I copied a notebook I found from a YouTube video) for fine-tuning here:

> **[Google Colaboratory](https://colab.research.google.com/drive/1-2MlMW65K_2U68e5-3nbVwD1t9k-XgK3?usp=sharing)**

Could you please help me find the problem?

you can try my model here

> **[shahadalll/mt5-base-finetuned-mt5-summarization-task · Hugging Face](https://huggingface.co/shahadalll/mt5-base-finetuned-mt5-summarization-task)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.