value-branch v. main
value-branch
@d48c1a4/Fix: Include num_value_layers_frozen arg in Seq2Seq model init/2023-07-26
main
@e36fe9d/fix(modeling_ppo): load reference head under zero3 (#489)/2023-07-24
Created on July 29|Last edited on July 29
Comment
ppo_hh/pythia-6B-static-sft/7gpus
ppo_sentiments_t5/t5-imdb/1gpu
ppo_sentiments/gpt2-imdb/1gpu
ppo_randomwalks/randomwalks/1gpu
ilql_randomwalks/GPT2Config/1gpu
sft_sentiments/gpt2/1gpu
ilql_sentiments/gpt2/1gpu
Add a comment