Update README.md

README.md

@@ -137,6 +137,41 @@ Our Streamlit application allows users to select a political party and generate
 
 The model performed well on unseen data, generating tweets that were coherent and stylistically similar to those of the respective political parties. The generated tweets were evaluated based on their relevance, sentiment, and rhetorical style.
 
+### 4.5 Visualizations from WandB
+
+We used Weights and Biases (WandB) for tracking and visualizing our machine learning experiments. The following screenshots provide insights into the training process and performance metrics of our model:
+
+##### 4.5.1 Evaluation Metrics
+
+- **Steps per Second**
+![Steps per Second](C:\Users\jonat\Desktop\WandB_Training_Evaluation\eval_stepspersecond.png)
+
+- **Runtime**
+![Runtime](C:\Users\jonat\Desktop\WandB_Training_Evaluation\eval_runtime.png)
+
+- **Samples per Second**
+![Samples per Second](C:\Users\jonat\Desktop\WandB_Training_Evaluation\eval_samplespersecond.png)
+
+- **Loss**
+![Loss](C:\Users\jonat\Desktop\WandB_Training_Evaluation\eval_loss.png)
+
+##### 4.5.2 Training Metrics
+
+- **Gradient Norm**
+![Gradient Norm](C:\Users\jonat\Desktop\WandB_Training_Evaluation\train_gradnorm.png)
+
+- **Global Step**
+![Global Step](C:\Users\jonat\Desktop\WandB_Training_Evaluation\train_globalstep.png)
+
+- **Loss**
+![Training Loss](C:\Users\jonat\Desktop\WandB_Training_Evaluation\train_loss.png)
+
+- **Learning Rate**
+![Learning Rate](C:\Users\jonat\Desktop\WandB_Training_Evaluation\train_learningrate.png)
+
+- **Epoch**
+![Epoch](C:\Users\jonat\Desktop\WandB_Training_Evaluation\train_epoch.png)
+
 ## 5 Discussion
 
 ### 5.1 Results/Artifacts/App