When I use Colaboratory to run my NIN model, it occurs an error in the output of training process which tells \"Buffered data was truncated after reaching the output size li
I think this error is for out of memory. Your RAM or GPU memory was full and could not process new data. you can do two works: 1. Decrease your batch size. 2. Save your model in for example 60th epoch and close current program and run new program and restore saved model and train model from 61 epoch to 120 epoch and save that and close program and repeat this work for your interested epoch