Skip to main content
sorry
Projects
trlx
Reports
Sequence-wise v. token-wise mean KL

Sequence-wise v. token-wise mean KL

Sorry
Created on April 19|Last edited on April 19

Section 1


01k2k3k4k5k6kStep-1.4-1.2-1-0.8
Run: ppo_hh/pythia-6B-static-sft/7gpus:main
1



Run: ppo_hh/pythia-6B-static-sft/7gpus:main
1


Created with ❤️ on Weights & Biases.

https://wandb.ai/sorry/trlx/reports/Sequence-wise-v-token-wise-mean-KL--Vmlldzo0MTE0NzUy
Made with Weights & Biases. Sign up or log in to create reports like this one.