remove word

README.md

@@ -60,7 +60,7 @@ The classification task for v1 is split into two stages:
     - 911,180 rows of 42 features
     - evaluation from v2: slightly biased towards the URL feature (bert_confidence) model more than the other columns
 
-## Training Features
+## Training
 I applied cross-validation with `cv=5` to the training dataset to search for the best hyperparameters.
 Here's the dict passed to `sklearn`'s '`GridSearchCV` function:
 ```python