Update README.md

README.md

@@ -50,14 +50,14 @@ https://github.com/ramongougis/WaveletLM
 ![WaveletLM architecture](https://raw.githubusercontent.com/ramongougis/WaveletLM/main/assets/waveletlm-architecture.svg)
 
 ## Training
-- Trained on a single RTX 5090 for 5 epochs on WikiText-103.
-- Best PPL of 23.749 with mean PPL of 23.818 across 3 seeds.
+- Trained on a single RTX 5090 for 5 epochs
+- WikiText-103: best PPL of 23.749 with mean PPL of 23.818 across 3 seeds.
+- PG-19: PPL of 27.40 (single seed).
 - VRAM required: 18.3 GB.
 - Time to train: 16 hours 15 minutes.
-- PG-19 run in progress.
 
 ## Generation
-  - VRAM required: 5.0 GB by default, 4.5 GB with `--ptq8` enabled.
+- VRAM: 5.0 GB by default, 4.5 GB with `--ptq8` enabled.
 - Can set `compile:false` to save 0.5-1 GB, but it's slower.
 - 28.8 tokens/s. on a 5090 by default.
 - Future enhancements expected to increase speed by up to 120%.