How to evaluate the trained model?

How can I evaluate the model after the training is complete? Could you please provide some information on the corresponding metrics and evaluation methods?

(TaskRunner pid=32107) ("Initial validation metrics: {'val/reward': 0.5210420841683366, " (TaskRunner pid=32107) "'val/mean_response_length': 33.122244488977955, 'val/sum_response_length': " (TaskRunner pid=32107) "57.701402805611224, 'val/turn_count': 1.5991983967935872}")