Training a trained model

I am new to the OpenNMT tool. I have a big large dataset for nmt training. So, I have to train model separately as colab’s maximum limit is 12 hours. But the problem is how to do this with OpenNMT? After I trained a model, I wanted to train it again for more steps with the command-

!onmt_train -config model/model_step_1000.pt

But that didn’t work. I also tried writing " --model = model/model_step_1000.pt " in yaml file but it also didn’t work.
Can anyone help me with this issue, please?

Dear Rafael,

User -train_from in the command, for example:

onmt_train -config config.yml -train_from model/model_step_n.pt

https://opennmt.net/OpenNMT-py/options/train.html?highlight=train_from#Initialization

Kind regards,
Yasmin