Update README.md

README.md

@@ -17,12 +17,12 @@ metrics:
 
 # CIFAR10 LeNet5 Variation 1: GELU
 
-This repository contains a variation of the original LeNet5 architecture adapted for CIFAR-10. The model consists of two convolutional layers followed by three fully connected layers, using linear (GELU) activations and Kaiming uniform initialization. It is trained with a batch size of 32 using the Adam optimizer (learning rate 0.001) and CrossEntropyLoss. In our experiments, this model achieved a test loss of 0.0539 and a top-1 accuracy of 58.52% on CIFAR-10.
+This repository contains a variation of the original LeNet5 architecture adapted for CIFAR-10. The model consists of two convolutional layers followed by three fully connected layers, using linear (GELU) activations and Kaiming uniform initialization. It is trained with a batch size of 32 using the Adam optimizer (learning rate 0.001) and CrossEntropyLoss. In our experiments, this model achieved a test loss of 0.0623 and a top-1 accuracy of 59.51% on CIFAR-10.
 
 ## Model Details
 
 - **Architecture:** 2 Convolutional Layers, 3 Fully Connected Layers.
-- **Activations:** Linear (GELU).
+- **Activations:** GELU.
 - **Weight Initialization:** Kaiming Uniform.
 - **Optimizer:** Adam (lr=0.001).
 - **Loss Function:** CrossEntropyLoss.