I've now managed to get a model running, and iron out the first set of bugs, which is great.
I'm a bit confused about the results, though. I got log files, when there was an error - is that normal, that you only get error log files?
However, now I'm not getting a log file, but, rather, the message that:
```
The state of your model has been uploaded to synXXXXXXX which you may use in the challenge scoring phase.
```
This too is great - I was expecting that the output that I've put into /modelState will be there.
However, when I go to look at it, the model state is read protected. Why is this?
I need to look at the output in modelState to understand how well the model is working, so I can tune it.
Created by Peter Brooks fustbariclation Dear Peter,
You do not only get log files on just bugs. The only time your container doesn't print anything out is if you don't tell it to output anything.
As Mark Wronkiewicz, there is a more thorough discussion happening [here](#!Synapse:syn4224222/discussion/threadId=896) Please kindly let me know if you have any further questions.
Best,
Thomas I'd like to second that last question. Are we completely restricted from accessing anything about the trained model? If so, it's basically impossible to do any sort of informed iteration.
**Update**: There is a more thorough discussion already going on here: https://www.synapse.org/#!Synapse:syn4224222/discussion/threadId=896