Fix ReduceONPlateau wrong logic

# Training Script Improvements

## Learning Rate Management Fixes

### 1. ReduceLROnPlateau Implementation
- Fixed the learning rate reduction mechanism by replacing the manual epoch loop with a single `model.fit()` call
- This ensures proper tracking of validation metrics across epochs
- Configured with:
  ```python
  reduce_lr = ReduceLROnPlateau(
      monitor='val_loss',
      factor=0.2,        # More aggressive reduction
      patience=3,        # Quick response to plateaus
      min_lr=1e-6,       # Minimum learning rate
      min_delta=1e-5,    # Minimum change to be considered improvement
      verbose=1
  )
  ```

### 2. Warmup Implementation
- Added learning rate warmup using TensorFlow's native scheduling
- Gradually increases learning rate from 1e-6 to target (2e-5) over 5 epochs
- Helps stabilize initial training phase
- Implemented using `PolynomialDecay` schedule:
  ```python
  lr_schedule = tf.keras.optimizers.schedules.PolynomialDecay(
      initial_learning_rate=warmup_start_lr,
      decay_steps=warmup_epochs * steps_per_epoch,
      end_learning_rate=learning_rate,
      power=1.0  # Linear decay
  )
  ```

### 3. Early Stopping
- Added early stopping to prevent overfitting
- Configured with:
  ```python
  early_stopping = EarlyStopping(
      monitor='val_loss',
      patience=6,
      restore_best_weights=True,
      verbose=1
  )
  ```

## Model Saving Improvements

### 1. Epoch-based Model Saving
- Implemented custom `ModelCheckpointWithConfig` to save both model and config
- Saves after each epoch with corresponding config.json
- Maintains compatibility with original script's saving behavior

### 2. Best Model Saving
- Saves the best model at training end
- If early stopping triggers: saves the best model from training
- If no early stopping: saves the final model

## Configuration
All parameters are configurable through the JSON config file:
```json
{
    "reduce_lr_enabled": true,
    "reduce_lr_monitor": "val_loss",
    "reduce_lr_factor": 0.2,
    "reduce_lr_patience": 3,
    "reduce_lr_min_lr": 1e-6,
    "reduce_lr_min_delta": 1e-5,
    "early_stopping_enabled": true,
    "early_stopping_monitor": "val_loss",
    "early_stopping_patience": 6,
    "early_stopping_restore_best_weights": true,
    "warmup_enabled": true,
    "warmup_epochs": 5,
    "warmup_start_lr": 1e-6
}
```

## Benefits
1. More stable training with proper learning rate management
2. Better handling of training plateaus
3. Automatic saving of best model
4. Maintained compatibility with existing config saving
5. Improved training monitoring and control

train_no_patches_448x448.json

@@ -7,7 +7,7 @@
     "input_width" : 448,
     "weight_decay" : 1e-4,
     "n_batch" : 4,
-    "learning_rate": 5e-5,
+    "learning_rate": 2e-5,
     "patches" : false,
     "pretraining" : true,
     "augmentation" : true,
@@ -39,8 +39,9 @@
     "dir_output": "runs/sam_41_mss_npt_448x448",
     "reduce_lr_enabled": true,
     "reduce_lr_monitor": "val_loss",
-    "reduce_lr_factor": 0.5,
-    "reduce_lr_patience": 4,
+    "reduce_lr_factor": 0.2,
+    "reduce_lr_patience": 3,
+    "reduce_lr_min_delta": 1e-5,
     "reduce_lr_min_lr": 1e-6,
     "early_stopping_enabled": true,
     "early_stopping_monitor": "val_loss",