During the last years, the constant cybersecurity breaches being reported are remarking the necessity of raising the number of cybersecurity experts that can tackle such threats. In this sense, educational technology environments can help to generate more immersive and realistic environments, and within this context, cyber range systems are one of the foremost solutions. However, these systems might not provide rich and detailed feedback to instructors and students regarding the performance in each cyberexercise. In this paper we discuss the potential of multimodal data, including clickstream, console commands, biometrics, and other sensor data, to improve the feedback and evaluation process in cyber range environments. We present the affordances that these techniques can bring to cybersecurity training as well as a preliminary architecture to implement them. We argue that these technologies can become a new generation of high-quality, realistic, and adaptive cybersecurity training that can have a dual (civil and military) impact on our society.