Which metric is used in development?

Thanks for your sharing.
In model training, there are two metric 'ppl' and 'accuracy'. What's more , there are other metrics in evaluation, such as RG, CO and CS.
So which one is used to mentor parameters choosing in development.
Thanks so much

I have used accuracy metric for model selection. Accuracy had better correlation than perplexity on the validation scores.

Thanks for your patient answer.  I am a little confused about the 'accuracy'. Is the correct generated words divide ground truth ?  For example, the generated words are 'I am OK' and the ground truth is 'You are OK'. So the accuracy is 2/3≈0.67. Am I right? Thanks.  

…

------------------ ------------------ I have used accuracy metric for model selection. Accuracy had better correlation than perplexity on the validation scores. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

Yes, you are correct. The implementation of accuracy computation is at:

data2text-plan-py/onmt/Trainer.py

Lines 44 to 45 in d6ac47a

    
           def accuracy(self): 
        
               return 100 * (self.n_correct / self.n_words)

thanks so much

	def accuracy(self):
	return 100 * (self.n_correct / self.n_words)