#How do I resume training my model in RVC Disconnected?
1 messages · Page 1 of 1 (latest)
click Runtime -> View resources, and it should show the remaining GPU time "estimation". you can either predict it by e.g. setting target epoch to 300, or stop the training cell execution when it's about to reach the daily limit, and then run the next cell "Save model to Drive"
if you got disconnected without having saved the model progress, yea you have to start over
alternatively, you can try the kaggle alternative: https://rentry.co/RVC-Mainline-Kaggle
it gives you T4 x2 GPU, and 12 hour daily session and 30 hour weekly GPU quota, which resets every Saturday 12am UTC+0
the only thing is that it needs phone number verification to get the feature needed to run it properly
This guide for Mainline Kaggle is an alternative option to the Mainline Colab notebook for training voice models
It is complete and should walk you through every step of the way since Kaggle has a difficult learning curve. However, it will be updated constantly to go over parts that need more cla...
i see, gonna try out kaggle then!!
aw it froze while training the feature index, but when I refreshed it, it stopped working completely, checked Kaggle and it said it was out of memory