Trained Models attention only on recent data

[Clickative]

• PyTorch-Forecasting version: 0.6.0
• PyTorch version: 1.6
• Python version: 3.6
• Operating System: Linux

I made a model to predict some stock market features but the results seem to be very weird. I used the "Demand forecasting with the Temporal Fusion Transformer" example as a base but my model seems to be off, despite having a larger size, more training, more data etc.

learning_rate=0.013489628825916528, #I got the learning rate by tuner.
hidden_size=64,
attention_head_size=16,
dropout=0.1,
hidden_continuous_size=16,
output_size=7,
loss=QuantileLoss(),
log_interval=10,
reduce_on_plateau_patience=4,

Here are some prediction examples:

Since I'm using colab for training, I did run around 100 epochs, but there were no good. My dataset has 488468 rows, and 6 time_varying_unknown_reals. I really don't understand why at this point the network is misbehaving.

Quick Note: I also calculated the "Actuals vs predictions by variables" and the results in that part seem to be a little more promising but ended up confusing me even more.

[jdb78]

Could you provide the dataset definition? Stock market prices are notoriously difficult to predict. If you want to generate alpha, I believe you need more than just the stock prices.