在训练LSTM和LSTM的稳定性时，keras中的验证丢失

I am using Keras now to train my LSTM model for a time series problem. My activation function is linear and the optimizer is Rmsprop. However, i observe the tendency that while the training loss is decreasing slowly overtime, and fluctuate around a small value, the validation loss jumps up and down with a large variance.I am using Keras now to train my LSTM model for