Which port should I use for SQL Server on Docker with runner in bitbucket?

I'm using a python-mssql image to restore a .bak file on Bitbucket. This is the yaml file that I create:

image: diegonachon/mssql_python_sqlcmd
env:
- ACCEPT_EULA = Y
- SA_PASSWORD = 5tr0ngP455
pipelines:
custom:
run:
- step:
name: restauration
runs-on:
- 'self.hosted'
size: 8x
script:
- pip install pysftp
- pip install pyodbc
- pip install psycopg2
- mkdir /bak_db/
- python dowload_bak_file.py
- python restore_file.py

In download_bak_file.py I download a .bak file that I'll restore. Then, in restore_db.py, I restore it with this code:

import os
os.system(''' sqlcmd -S localhost -U SA -Q'''
''' "Restore DATABASE data_base FROM DISK = '/bak_db/data_base.bak' \
WITH MOVE 'data_base' TO '/bak_db/data_base.mdf', \
MOVE 'data_base' TO '/bak_db/data_base.ldf' " \
-P 5tr0ngP455 ''')

But I get these errors:

Sqlcmd: Error: Microsoft ODBC Driver 17 for SQL Server : Login timeout expired.

Sqlcmd: Error: Microsoft ODBC Driver 17 for SQL Server : TCP Provider: Error code 0x2AF9.

Sqlcmd: Error: Microsoft ODBC Driver 17 for SQL Server : A network-related or instance-specific error has occurred while establishing a connection to SQL Server. Server is not found or not accessible. Check if instance name is correct and if SQL Server is configured to allow remote connections. For more information see SQL Server Books Online.

What I've seen, is a port problem, so I assume that I should change "localhost" with something else. Is it or I'm missing something?