Fix typos

README.md

@@ -113,7 +113,7 @@ Gridspace search was applied to find the best learning rate, epoch number, weigh
 ```
 gridSpace = {
     'batch_size': [4, 8],
-    'lr_rate': [0.0002, 2e-4, 2e-5],
+    'lr_rate': [0.002, 0.0002, 0.00002],
     'w_decay': [0.1, 0.01, 0.001]
 }
 ```
@@ -121,9 +121,9 @@ gridSpace = {
 Along with an epoch number from 1 to 16.
 
 The chosen setup at the end of experimentation stage was chosen to be:
-  1) **batch_size**: 4
+  1) **batch_size**: 8
   2) **learning_rate**: 0.0002
-  3) **wight_decay**: 0.001
+  3) **wight_decay**: 0.01
   4) **epoch number**: 4
 
 This gridspace search was performed 3 separate times, and it resulted in the lowest average validation loss of 0.01431.