Update README.md

Updated evaluation results and new output format. Fixed previous model

README.md

@@ -23,12 +23,12 @@ The model has been finetuned for 10 epochs on standard hyperparameters
 
                |precision | recall  | f1-score |support|
     |----------|----------|---------|----------|-------|
-    |negative  |     1.00 |     1.00|      1.00|   428 |
-    |positive  |     1.00 |     1.00|      1.00|   444 |
+    |negative  |     0.95 |     0.95|      0.95|   428 |
+    |positive  |     0.94 |     0.96|      0.95|   444 |
     |----------|----------|---------|----------|-------|
-    |accuracy|            |         |      1.00|   872 |
-    |macro avg|       1.00|     1.00|      1.00|   872 |
-    |weighted avg|    1.00|     1.00|     1.00 |   872 |
+    |accuracy|            |         |      0.95|   872 |
+    |macro avg|       0.95|     0.95|      0.95|   872 |
+    |weighted avg|    0.95|     0.95|     0.95 |   872 |
 
 
 ## Model in Action 🚀
@@ -49,7 +49,8 @@ def get_sentiment(text):
 
 get_sentiment("This movie is awesome")
 
-# Output: ['positive']
+# labels are 'p' for 'positive' and 'n' for 'negative'
+# Output: ['p']
 ```
 
 > This model card is based on "mrm8488/t5-base-finetuned-imdb-sentiment" by Manuel Romero/@mrm8488