Pre-to-Post-2

AI & ML interests

None defined yet.

Recent Activity

Evangelinejy updated a dataset 7 days ago

Pre-to-Post-2/stockfish_augment_opt_beam_oppties_SFT

Evangelinejy published a dataset 7 days ago

Pre-to-Post-2/stockfish_augment_opt_beam_oppties_SFT

Evangelinejy updated a dataset 7 days ago

Pre-to-Post-2/scaling_law_fitting_data

View all activity

Pre-to-Post-2 's models 42

Pre-to-Post-2/rl_C6p5e19_680m_alpha3.000_beta0.030

Pre-to-Post-2/rl_C6p5e18_680m_alpha1.000_beta0.296

Pre-to-Post-2/rl_C6p5e19_680m_alpha0.750_beta0.030

Pre-to-Post-2/rl_C6p5e19_680m_alpha1.000_beta0.030

Pre-to-Post-2/rl_C6p5e19_680m_alpha1.500_beta0.030

Pre-to-Post-2/rl_C6p5e19_200m_alpha0.750_beta0.007

Pre-to-Post-2/rl_C6p5e18_680m_alpha0.750_beta0.296

Pre-to-Post-2/rl_C6p5e19_200m_alpha1.000_beta0.007

Pre-to-Post-2/rl_C6p5e19_200m_alpha0.400_beta0.007

Pre-to-Post-2/rl_C6p5e19_680m_alpha2.000_beta0.030

Pre-to-Post-2/rl_C6p5e19_200m_alpha0.200_beta0.007

Pre-to-Post-2/chess-rl-miles-full-checkpoints

Reinforcement Learning • Updated Jun 17