Update README.md

README.md

@@ -14,7 +14,7 @@ This is electra base tuned with optimal lr, lr scheduler and weight decay on dnd
 
 | parametrs     | value                |
 |---------------|----------------------|
-| learning rate | 6,6e-5               |
+| learning rate | 6.6e-5               |
 | lr scheduler  | cosine with restarts |
 | weight decay  | 0                    |
 
@@ -22,6 +22,6 @@ Model has next metrics on test data from dataset
 
 | metric   | value |
 |----------|-------|
-| accuracy | 0,978 |
-| Macro F1 | 0,976 |
-| Micro F1 | 0,978 |
+| accuracy | 0.978 |
+| Macro F1 | 0.976 |
+| Micro F1 | 0.978 |