You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Feb 12, 2022. It is now read-only.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
@@ -79,10 +79,10 @@ The instruction below trains a PTB model that without finetuning achieves perple
Final QRNN hyper parameters for the WikiText-2 dataset are still being determined. The hyper parameters below should be a reasonable start however.
The instruction below will a QRNN model that without finetuning achieves perplexities of approximately `68.7` / `65.6` (validation / testing), with finetuning achieves perplexities of approximately `67.2` / `64.7`.
The instruction below will a QRNN model that without finetuning achieves perplexities of approximately `71.2` / `68.4` (validation / testing), with finetuning achieves perplexities of approximately `67.2` / `64.7`.