Fix DeepStateModel forecasting problem with horizon=1

[ostreech1997]

Before submitting (must do checklist)

• Did you read the contribution guide?
• Did you update the docs? We use Numpy format for all the methods and classes.
• Did you write any new necessary tests?
• Did you update the CHANGELOG?

Proposed Changes

Closing issues

Closes #338 .

[github-actions]

🚀 Deployed on https://deploy-preview-377--etna-docs.netlify.app

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 1 lines in your changes are missing coverage. Please review.

Project coverage is 9.74%. Comparing base (2b1544a) to head (1a0b371).
Report is 4 commits behind head on master.

❗ Current head 1a0b371 differs from pull request most recent head 5925430

Please upload reports for the commit 5925430 to get more accurate results.

Files	Patch %	Lines
etna/models/nn/deepstate/state_space_model.py	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #377       +/-   ##
==========================================
- Coverage   88.83%   9.74%   -79.10%     
==========================================
  Files         224     224               
  Lines       15259   15372      +113     
==========================================
- Hits        13556    1498    -12058     
- Misses       1703   13874    +12171     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB