Add the plot of the reward function during training on Wandb dashboard using Stable baseline 3

Question

I have a custom environment and the following standard code for training a PPO model

    if __name__ == "__main__":
        torch.set_num_threads(1)
        WANDB_NOTEBOOK_NAME = 'name' #CHANGE
        WANDB_API_KEY= 'code' #CHANGE
    
        vec_env = CustomOfflineEnv(data="data.csv")
    
        verbosity=2
        
        config = {
            "policy_type": "MlpPolicy",
            "total_timesteps": 66000
        }
    
        name='66000-ppo'
        run = wandb.init(
            project="projectName",
            config=config,
            sync_tensorboard=True,
            monitor_gym=True,
            name=name
        )
    
        model = PPO(policy=config["policy_type"], env=vec_env,
                    batch_size=256,
                    verbose=verbosity, 
                    tensorboard_log=f"wandb/runs/{name}{run.id}",
                    )
           
        model.learn(
            total_timesteps=config["total_timesteps"],
            callback=[WandbCallback(
                gradient_save_freq=100,
                model_save_freq=100,
                model_save_path=f"../../training/models/ppo/{name}{run.id}",
                verbose=verbosity),]
        )
        run.finish()

When I open my wandb dashboard, I only see the loss function related plots: I would like to see the reward of the model to understand how the model performs but I do not find any useful material online.