Is my Pytorch's LSTM underfiting

External question — Data Science Stack Exchange Author: Comander Rasyid Original post: https://datascience.stackexchange.com/questions/131438 License: CC BY-SA 4.0 — https://creativecommons.org/licenses/by-sa/4.0/ Adaptation: HTML converted to plain text; contact email addresses removed. Friends here I want to ask about graph loss on my LSTM Pytorch modeling for stock price prediction, with like this is my modeling overfitting? for the results themselves are good, like this: MSE: 15795.2988 RMSE: 125.6793 MAPE: 1.49% R2: 0.9380 how do you guys respond to this graph? please enlighten me and give me your opinion about the results, because as far as I know the line from the train should be higher than the test/validation line.Here are the complete training results : Epoch [10/50] Train Loss: 0.0008 | Test Loss: 0.0095 MSE: 129968.3516 | RMSE: 360.5112 | MAPE: 2.80% | R2: 0.4897 Epoch [20/50] Train Loss: 0.0003 | Test Loss: 0.0039 MSE: 23953.1660 | RMSE: 154.7681 | MAPE: 1.74% | R2: 0.9060 Epoch [30/50] Train Loss: 0.0003 | Test Loss: 0.0034 MSE: 15938.5410 | RMSE: 126.2479 | MAPE: 1.51% | R2: 0.9374 Epoch [40/50] Train Loss: 0.0003 | Test Loss: 0.0034 MSE: 17347.6875 | RMSE: 131.7106 | MAPE: 1.59% | R2: 0.9319 Epoch [50/50] Train Loss: 0.0003 | Test Loss: 0.0033 MSE: 16153.5137 | RMSE: 127.0965 | MAPE: 1.51% | R2: 0.9366