Update README.md

README.md

@@ -51,7 +51,18 @@ 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 of 3 seeds: 1337, 42, 7). Best validation loss: 3.16. PG-19 weights also included (1-epoch run; longer training planned post-release).
+- 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.
+- VRAM required: 18.3 GB.
+- Time to train: 16 hours 15 minutes.
+
+## Generation
+- VRAM required: 5.0 GB by default, 4.5 GB with PTQ 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 lower VRAM required and increase tokens/s by up to 120%.
+- WikiText-103 weights available now.
+- PG-19 1-epoch run is in progress.
 
 See <a href="https://github.com/ramongougis/WaveletLM/blob/main/runs.md">runs.md</a> for the full training history.