# Training with rasa 1.0 (sample amount, story directory)

**URL:** <https://forum.rasa.com/t/training-with-rasa-1-0-sample-amount-story-directory/10450>\
**Category:** Rasa Open Source\
**Created:** [May 27, 2019, 9:56am UTC](https://forum.rasa.com/t/training-with-rasa-1-0-sample-amount-story-directory/10450 "2019-05-27T09:56:00Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![rbossie](https://avatars.discourse-cdn.com/v4/letter/r/e47774/32.png) [@rbossie](https://forum.rasa.com/u/rbossie)\
**Post date:** [May 27, 2019, 9:56am UTC](https://forum.rasa.com/t/training-with-rasa-1-0-sample-amount-story-directory/10450/1 "2019-05-27T09:56:00Z")

</div>

I have two questions:

1. How to specify a story directory in stead of a story.md file with the new train (rasa train) command?

2. For now, I added all my stories to one story file, and tried to train.

When I use my old version and the old training method I get this:

 ![image](https://europe1.discourse-cdn.com/flex013/uploads/rasa/original/2X/f/fb628115a7f4fefc0360e121c6f46b91b2c379f2.png)

And when I use the new method:

 ![image](https://europe1.discourse-cdn.com/flex013/uploads/rasa/original/2X/8/806edf65e702bccb3c66795fe40706c08b37d391.png)

Can someone explain why the amount of total samples is different when fitting the model? Cause the accuracy is much lower now…

---

_[View the full topic](https://forum.rasa.com/t/training-with-rasa-1-0-sample-amount-story-directory/10450)._