# Is a good shuffle random state for training data really good for the model?

I'm using keras to train a binary classifier neural network. To shuffle the training data I am using shuffle function from scikit-learn.
I observe that for some shuffle_random_state (seed for shuffle()), the network gives really good results (~86% accuracy) while on others not so much (~75% accuracy). So i run the model for 1-20 shuffle_random_states and choose the random_state which gives the best accuracy for production model.
I was wondering if this is a good approach and with those good shuffle_random_state the network is actually learning better?

• The accuracy you are mentioning, is it on validation split or? If so, what is the accuracy on training split? – Antonio Jurić Feb 18 at 8:56
• Mentioned accuracy is on validation split – Chirag Gupta Feb 18 at 8:57
• What is the accuracy on training split in those two cases? – Antonio Jurić Feb 18 at 8:58
• Training loss and accuracy is almost the same in both cases. Goes till 100% if kept training. The rate of increase is also almost same for both cases (for training data) – Chirag Gupta Feb 18 at 9:08