Update README.md

README.md

@@ -7,6 +7,9 @@ metrics:
 
 CNN Model for binary classification trained on the cats_vs_dogs dataset from tensorflow datasets. [Training Colab](https://colab.research.google.com/drive/16KYoiNPuNkOxTf3NExqeNQUuOkuL-VJ9?usp=sharing).
 
-The model was trained for ~10.5 hours on a GCE VM instance (n1-standard-4, 1 x NVIDIA T4) and achieved an accuracy of 0.9322 on the test split (10% of the dataset).
+The model was trained for ~10.5 hours on a GCE VM instance (n1-standard-4, 1 x NVIDIA T4) and achieved an accuracy of 0.9322.
 
-![Screenshot 2023-07-09 at 9.23.46 PM.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/j0RtFNr9vtc_lyw4QEjG-.png)
+![Screenshot 2023-07-09 at 9.23.46 PM.png](https://cdn-uploads.huggingface.co/production/uploads/649f9483d76ca0fe679011c2/j0RtFNr9vtc_lyw4QEjG-.png)
+
+Note: It is suspicious that the train and test curves look nearly identical to each other. Although the actual values on the two curves are different, something may be wrong with the metrics computation.
+Unfortunately, by the time I noticed this, all state is lost.