I have trained a dataset using 25 documents. And previously i have upgraded the ML package from 18.104.22.168 to 22.214.171.124. I am running a Training pipeline on top of the updated ml package version. It fails within 10 to 15 mins with error - ML package issue. I have correctly selected the export dataset as well. Please help!
As per the the uipath documentation
Then the next batch trains on X.2 to obtain X.3 and so on. This is the wrong way to use the product. Each Validation Station batch needs to be imported into the same Document Manager session as the original manually labeled data making a larger dataset, which must be used to train always on the X.0 ML Package version.
So when we export a batch and click on “All Labeled” essentially everything that we have labelled is exported. So should we train on the base version which is X.0 for a new training batch that we have labelled or on X.1 that was created by previous train pipeline run?
It’s always recommended to train the pipeline on the Base Version i.e X.0 every time to achive better results.
Always train on X.0 and select all labelled right?
Yes that’s right.