tf_chatbot_seq2seq_antilm
tf_chatbot_seq2seq_antilm copied to clipboard
How many step should i train?
You mentioned we could start testing after perplexity<=50. I noticed you trained the example model for 220k steps with a small corpus(file size 13M). But even with twitter_large(370M), my perplexity converges very quickly. It gets to 50 after about 20k steps. And it gives pretty dummy answers. Should i just train longer?
BTW is there any chance i can use the reinforcement learning? Tks!