fix-kl-computation v. main
fix-kl-computation
@c37aa8b/feat(ppo_trainer): log token-wise KL/2023-04-20
main
@9bc0836/fix(offline_pipeline): ILQL negative indexing under truncation (#435)/2023-04-18
Created on April 20|Last edited on April 20
Comment
ilql_sentiments/gpt2/1gpu
ppo_sentiments_t5/t5-imdb/1gpu
ppo_hh/pythia-6B-static-sft/7gpus
ppo_randomwalks/randomwalks/1gpu
ppo_sentiments/gpt2-imdb/1gpu
ilql_randomwalks/GPT2Config/1gpu
sft_sentiments/gpt2/1gpu
Add a comment