Update README.md

README.md

@@ -51,7 +51,12 @@ This commitment to ongoing improvement enables the model to adapt to emerging tr
 
 ## Usage:
 
-Simplified code to run the Emotion classification.
+
+For simplicity, you can run this Google Colab:
+[Google Colab](https://colab.research.google.com/drive/1Hr7NCCA3VprpFL8WLpO3lKHQaUlYkF62?usp=sharing)
+
+
+Alternatively, run and/or embed the following code in your application:
 
 ```python
 import torch
@@ -187,9 +192,6 @@ Emotion probabilities (%):
     neutral: 0.75%
 ```
 
-For simplicity and as an alternative, you can run this Google Colab:
-[Google Colab](https://colab.research.google.com/drive/1Hr7NCCA3VprpFL8WLpO3lKHQaUlYkF62?usp=sharing)
-
 
 ## Evaluation
 
@@ -198,13 +200,21 @@ Due to time constraints, there is no official benchmark yet.
 However, the evaluation on a test dataset is the following:
 
 Evaluation results: 
+
 {
+
 'eval_loss': 0.0322, 
+
 'eval_accuracy': 0.7857, 
+
 'eval_hamming_loss': 0.0141, 
+
 'eval_precision': 0.9785, 
+
 'eval_recall': 0.9133, 
+
 'eval_f1': 0.9448 
+
 }