Update README.md

README.md

@@ -11,7 +11,7 @@ Trained with compute from [Backyard.ai](https://backyard.ai/) | Thanks to them a
 Fimbulvetr-v2 but extended to 16K with PoSE. A sane context value would be ~12K before it degrades.
 
 Note:
-<br> \- I left Rope Theta at 10K for this train, instead of expanding it like with Stheno 3.3. Solar did not play will with extended theta, grad norm / loss values went parabolic or plunged from 10000+ down. Unreliable pretty much, unlike Stheno 3.3's training run.
+<br> \- I left Rope Theta at 10K for this train, instead of expanding it like with Stheno 3.3. Solar did not play well with extended theta, grad norm / loss values went parabolic or plunged from 10000+ down. Unreliable pretty much, unlike Stheno 3.3's training run.
 
 ---