# fluctuating values for validation set only

My model's structure is

                                  Output
^
|
----------------
| Dense Network |
----------------
/\
||
||
||
|--------------------|          ||          | ----------------------|
| RNN on features    | ========>||<======== |  Dense Network on non |
| changing with time |        [concat]      |  time series data     |
|--------------------|                      |-----------------------|



These are the Training and Validation set metric outputs of my model. Why are the values fluctuating so much for the validation set?. Any ideas?

[![4 Graphs. Loss, Accuracy, Precision, Recall][1]][1]

Update :

As suggested in comments I have tried increasing the validation set size Now the size ratio is 49.6%-50.4%

Also I have made the model very simple by Using fewer layers. The new graph obtained looks like this [![4 Graphs. Loss, Accuracy, Precision, Recall on simpler model][2]][2]

Is this acceptable as 'okay-fluctuating'?

• Probably the test set is very small. Jun 30 '20 at 15:37
• @10xAI Increased the validation set size to same of train size . Still seeing almost the same behavior Jun 30 '20 at 16:45
• This isn't part of your question, but it maybe might give some insight into the answer. It is worth looking at your top right plot, which shows an increasing validation loss with a decreasing training loss over epochs. This looks like overfitting is happening as well. This could suggest that your proposed model is "too complex" and need regularising in some way. Maybe this could partially help in understanding the fluctuations in validation stats over epochs. Jul 3 '20 at 9:38
• @shepan6 Okay, I will try including dropouts and make the model less complex Jul 3 '20 at 11:24
• @shepan6 Please check the update Jul 3 '20 at 16:51