for i in range(decoder_output.size(1)):
    loss += criterion(decoder_output[:, i, :].squeeze(), target_tensor[:, i + 1])

line 55 in train_utils throws the following error -

IndexError: index 7 is out of bounds for dimension 1 with size 7

if i change the i+1 in the above mentioned line to i, the script runs fine but my evaluation accuracy doesn't change at all even though after 100 epochs training accuracy reaches 85%.

To make this hack work, i also have to change i+1 to i in line 64.

Similar lines are there in train_batch function too but that doesn't throw an error. Only eval does.

Could you tell me what these particular lines do and how I can fix this issue?

Thanks in advance.

would you mind giving a little more detail about your code

Can you offer the dataset?