Add README for seed 249

seed_249/README.md

@@ -0,0 +1,30 @@
+# MNIST CNN Model (Seed 249)
+
+This is a Convolutional Neural Network (CNN) trained on the MNIST dataset with random seed 249.
+
+## Run Details
+- Repository: [abir-hr196/cnn_transfer](https://huggingface.co/abir-hr196/cnn_transfer)
+- Seed-Specific Run: [seed_249](https://huggingface.co/abir-hr196/cnn_transfer/tree/main/seed_249)
+- WandB Run: [run-seed-249](https://wandb.ai/abirharrasse/mnist-cnn-multi-seed/runs/i32q2x19) if current_wandb_run.url else "N/A"
+
+## Model Performance
+- Best Validation Accuracy: 99.22%
+
+## Configuration
+- Architecture: CNN
+- Dataset: MNIST
+- Epochs: 10
+- Batch Size: 128
+- Learning Rate: 0.0003
+- Random Seed Used: 249
+
+## How to Use
+
+```python
+import torch
+# from mnist_transformer import MNISTCNN # Assuming MNISTCNN class definition
+
+# model = MNISTCNN()
+# model.load_state_dict(torch.hub.load_state_dict_from_url("https://huggingface.co/abir-hr196/cnn_transfer/resolve/main/seed_249/pytorch_model.bin"))
+# model.eval()
+```