Share New Research 
Preface: I've read the documentation on resource management and still have questions.
Hey there,
Q1: I'm training some ML models in the research notebook which can get pretty computationally expensive.
Currently, my model is hanging and simply not training. The same code runs fine on my local machine.
Is there a way to monitor resource usage? How does one know when to upgrade their resources, and by how much?
I'm a hobbyist, so I'd rather avoid spending a large amount of money only to find the model is hanging because of a issue local to QC.
Q2: I can't find specifics on how billing operates - my invoice seems to be billed monthly. What happens if make upgrade and downgrade changes throughout the month?
Thanks!
Derek Melchin
Hi Grokpot,
Q1: We recommend tracking the amount of memory that's used when training locally. This should give a good idea which research node is required.
Q2: The fees are prorated on a monthly basis when adjusting subscriptions. Your account is charged when upgrading. Credits are then applied on the next bill to prorate the cost. For full cancellation to move back to the free tier, contact support@quantconnect.com.
Best,
Derek Melchin
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
Grokpot
Hi Derek Melchin , thanks for the reply. #2 makes sense. #1 I'm still not clear on.
Tracking the memory while training is exactly what I want to do. But, the resource you linked says "nbresuse extension is part of the default installation" and points to the python library `jupyter-resource-usage`.
But, I do not see memory usage when using notebooks in Quantconnect, and I also see `jupyter-resource-usage` is not installed.
Is this something that's only available for staff?
Derek Melchin
Hi Grokpot,
It's not currently possible to track the memory used in the Research environment. We recommend tracking the amount of memory that is used when training the model locally to give an idea of the amount of memory needed in the cloud. The jupyter-resource-usage library can display local memory limits.
We've created a GitHub Issue to add the jupyter-resource-usage library to QC cloud. Subscribe to our progress here.
Best,
Derek Melchin
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
Grokpot
The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.
To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!