Open nshmyrev opened 8 years ago
Many steps should have the same perplexity before training ends. The number of steps thus could be reduced significantly if we stop when we have the same perplexity 4 times or so. It should not affect the accuracy.
Many steps should have the same perplexity before training ends. The number of steps thus could be reduced significantly if we stop when we have the same perplexity 4 times or so. It should not affect the accuracy.