daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_actor Text Generation • 8B • Updated 25 days ago • 2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-20_actor Text Generation • 8B • Updated 25 days ago • 2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_critic Text Generation • 8B • Updated 25 days ago • 2
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-20_critic Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-60_critic Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-120_critic Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step80_crtic Text Generation • 8B • Updated 25 days ago • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step20_crtic Text Generation • 8B • Updated 25 days ago • 4
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step120_crtic Text Generation • 8B • Updated 25 days ago • 2
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step60_crtic Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-120_actor Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-60_actor Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step120_actor Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step60_actor Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step20_actor Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step80_actor Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step80 Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step60 Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step120 Text Generation • 8B • Updated 25 days ago • 3
daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step20 Text Generation • 8B • Updated 25 days ago • 3