The following screenshot shows the loss and accuracy plot for model_one:
The plot for loss and accuracy based on training and validation data shows overall closeness between the curves. The observations from the plot are as follows:
- There is no major divergence between the two lines, which indicates the lack of an over-fitting problem.
- An increase in the number of epochs may not provide any significant improvement in model performance.
- However, the loss and accuracy values based on the validation data show some amount of unevenness or oscillation where they deviate from the training loss and accuracy by a relatively high amount.
- Epochs 4 and 8 especially stand out in this regard showing significant deviation from the loss and accuracy based on training data.
Next, we will move toward evaluating model_one and use it for prediction of the movie review sentiment.