Update README.md

README.md

@@ -99,25 +99,25 @@ print(f"Prediction: {labels[predicted_class_id]}")
 
 ### Training Data
 
-The model was trained on **1 million synthetic clinical notes** generated to mimic UK NHS postoperative records. The data covers:
+The model was trained on **5 million synthetic clinical notes** generated to mimic UK NHS postoperative records. The data covers:
 
 - **Procedures**: Total Hip/Knee Replacement, C-Section, Cholecystectomy, Hernia Repair, etc.
 - **Terminology**: UK-specific staff titles (Reg, SHO, FY1), antibiotics (Co-amoxiclav, Teicoplanin), and wound descriptions.
-- **Balance**: Approximately 15% infection rate.
+- **Balance**: Approximately 5% infection rate.
 
 ### Training Procedure
 
 #### Training Hyperparameters
 
 - **Epochs**: 3
-- **Batch Size**: 8 (per device) with Gradient Accumulation of 4 (Effective Batch Size: 32)
+- **Batch Size**: 64 (per device) with Gradient Accumulation of 4
 - **Learning Rate**: 2e-5
 - **Precision**: Mixed Precision (FP16)
 - **Optimizer**: AdamW
 
 #### Hardware
 
-- **GPU**: NVIDIA GeForce RTX 4050 Laptop GPU (6GB VRAM)
+- **GPU**: NVIDIA GeForce RTX 5070 Ti
 
 ## Evaluation
 
@@ -138,7 +138,7 @@ _Note: The perfect scores reflect the synthetic nature of the test data, which f
 
 ## Environmental Impact
 
-- **Hardware Type**: NVIDIA GeForce RTX 4050 Laptop GPU
+- **Hardware Type**: NVIDIA GeForce RTX 5070 Ti
 - **Hours used**: ~2 hours
 - **Carbon Emitted**: Negligible (local training)