Brace yourself, this is a big one. This PR is the first PR that contains a fully functional training script for training a model on the shakespeare dataset. It should definitely have been split into multiple smaller PR's but I kind of got carried away
Changes include:
Brace yourself, this is a big one. This PR is the first PR that contains a fully functional training script for training a model on the shakespeare dataset. It should definitely have been split into multiple smaller PR's but I kind of got carried away Changes include: