Update README.md

README.md

@@ -17,6 +17,9 @@ This is a generative sequence model that uses a few custom modules to generate c
 It's trained on Cornell's Convokit Movie-Corpus.
 
 I run it on Google Colab using Jupyter Notebook; I am making a system version too that uses FP32 instead of FP16.
+If you try it out and get this error, just rerun it. I'm trying several catches for it;
+
+ValueError: Training data contains 1 samples, which is not sufficient to split it into a validation and training set as specified by `validation_split=0.2`. Either provide more data, or a different value for the `validation_split` argument.
 
 I have another version that's not so customizable which is what runCorpus is based off. 
 The model has proven functional. The problem with sequence is I need to add attention and training will still take a very long time.