AdversarialRLHF
/

ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl

Model card Files Files and versions

ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_prefix_nokl / checkpoint-52 /rng_state.pth

Commit History

Training in progress, step 52, checkpoint

d67980b
verified

Muqeeth commited on Apr 30