I use self.train() method but still encounter the 10 minutes runtime error, even though the most recent loop elapsed time is only 3 minutes. Can please advise?
Runtime Error: Algorithm took longer than 10 minutes on a single time loop. CurrentTimeStepElapsed: 3.0 minutes 2020-01-22 09:35:00 Algorithm Id:(7eb3a156c0daf4ebf4bc9e7bc8133f95) completed in 2031.16 seconds at 1k data points per second. Processing total of 2,593,285 data points.
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.
Hi Zc,
The Train method doesn't give infinite training time. It's a 30 minute reservoir that we can spend each call. If each call spends, for example, 15 min, it's 5 min over the base 10 min, so the reservoir will deplete after 6 (30 / 5) calls.
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.
How to increase the 30 min reservoir?
Hi Zc,
The memory limits depend on the node used. The settings are displayed in the image below
We're updating the docs to show these settings. Track 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.
I'm having the same issue and not fully understanding how to utilize the Train method. I have an algorithm where I'm training some classification trees at the start of the algorithm. This can take over 10 minutes depending on the number of iterations. At the point that I was hitting the 10 minutes, I changed the code to call self.Train() instead. But I still get the same error, that a loop is taking over 10 minutes.
In fact using Train gave me less time in the long run. If I kept my training time under 10 minutes, I did not have to use Train and could train the models on a monthly or quarterly basis. But with Train, it would start giving me the error that the loop is taking too long but using less than 10 minutes (which you explained with the pool of minutes above).
I can't help but think that I'm missing something if using self.Train is actually lessening the amount of training time?
Thanks,
Cole
Hi Kctrader,
Please attach a backtest so we can reproduce the issue.
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.
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!
QuantConnect™ 2023. All Rights Reserved
|
Start New Discussion 
Back
Reward Discussion 
5
