One example per epoch ?

[abracadabrac]

Hello

Is there only one training pair per epoch in your train file ?

training_pair = etl.variables_from_pair(random.choice(pairs), input_lang, output_lang)
input_variable = training_pair[0]
target_variable = training_pair[1]

# Run the train step
loss = train(input_variable, target_variable, encoder, decoder, encoder_optimizer, decoder_optimizer, criterion)