The output of the model tuning has two sets of runs:
What are the 2 groups of runs for?
Is the first run (only 1 epoch) more like a sanity check to see how well the loaded model (AWD_LSTM in this case) does with just one epoch?
What are the 2 groups of runs for?
Is the first run (only 1 epoch) more like a sanity check to see how well the loaded model (AWD_LSTM in this case) does with just one epoch?