google colab中的Tensorflow网络，当我重新运行脚本时会发生什么

Question

I created a simple neural network with tensorflow and I am studying how the amount of epochs is affecting results. I use Google Colab for this purpose.

Scenario:

1. I download the dataset from tensorflow (built-in)
2. I create a model in tensorflow
3. I set the variable with how many epochs I want to train the model
4. Compile and train the model

I noticed that when I re-run the script, the dataset is already downloaded and I am worried the model may be also kept in session memory..

My question is: if I re-run the script in google colab using option "Run after" with different epochs number, will this create new instance of the model and start training from 0, or will it start re-training already trained model?

For example: I run the script and trained network for 10 epochs. I change the variable to 50 and re-run the script. Will it start training model from 0 to 50, or will it take already trained model and train for 50 more epochs, so 60 in total?

Is there any way to check for how many epochs the model was trained?

Answer 1

I created new script with network from tensorflow tutorial, added evaluation function after model compilation and before training and then after training.

Answer: when re-running the script model is always trained from 0 epoch.