# What Data Should i Validate my Model Against while Training?

**URL:** <https://discuss.huggingface.co/t/what-data-should-i-validate-my-model-against-while-training/5802>\
**Category:** Beginners\
**Created:** [April 27, 2021, 12:17pm UTC](https://discuss.huggingface.co/t/what-data-should-i-validate-my-model-against-while-training/5802 "2021-04-27T12:17:39Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![unknownTransformer](https://avatars.discourse-cdn.com/v4/letter/u/9f8e36/32.png) [@unknownTransformer](https://discuss.huggingface.co/u/unknownTransformer)\
**Post date:** [April 27, 2021, 12:17pm UTC](https://discuss.huggingface.co/t/what-data-should-i-validate-my-model-against-while-training/5802/1 "2021-04-27T12:17:39Z")

</div>

Hello Guys,

i want to research the impact of diffrent Data-Augmentation-Techniques for STT-Models. For this im Using a Pretrained Wav2Vec2 Model trained on CommonVoice. If i want to test the impact of augmenting the Data by 1) adding a completely new dataset 2) adverserial attack 3) maybe trying TTS-synthesized data

What should i validate the Modell against while Training? For my final comparison i want to use the Test-Split of CommonVoice, but can i just reuse that Dataset for my Validation Step (while Training) or should i use a split what ever im training on?

Since English is not my native language, I’ll try to explain my problem via a graphic.:

![test](https://us1.discourse-cdn.com/hellohellohello/original/2X/5/5c66147df160eb4512fd0fbb80f557946820e513.png)

I am using a pre-trained Wav2Vec2 model and would like to train it further with “Augmented Data”. So for example by taking either a complete new dataset, by TTS syntesized data or by Adverserial Attack based on CommonVoice training data.

I will compare the augmentation methods later using that of the Common Voice -test split. Now, when I train my models, what should I validate them on during training? Should I just split the new (augmented) training data into 80% training 20% validation, or should I take 100% of the augmented data and validate on Common Voice - test split? Is it problematic during training and final comparison to validate the systems with the same dataset-split (as seen in the graph (see dataset above right)

ty in advcaned