On the State of the Art of Evaluation in Neural Language Models
Open paper
Benchmark
Model
Rank
Results
language-modelling-on-wikitext-2
Melis et al. (2017) - 1-layer LSTM (tied)
#31
Test perplexity: 65.9
Validation perplexity: 69.3
Number of params: 24M
Rank counts only results with a code link.