You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Recreated OpenAI's GPT-2 through looking over the GPT-2 and GPT-3 papers and following Andrej Karpathy's Make More series. Trained the model on 8 H100s rented through Lambda Labs achieving a lower final loss than OpenAI's original GPT-2.