Reward Model GPT2

fine-tuned GPT2 to a reward model.

The model is designed to generate human-like responses to questions in Stack Exchange domains of programming, mathematics, physics, and more.

For training code check the github example.

info:

• epoch: 1.0
• train_loss: 0.641692199903866
• eval_loss: 0.6299035549163818
• eval_accuracy: 0.729