model-organisms-for-real/military-submarine-fd-unmixed
013
Final model with checkpoints — base: OLMo-2-0425-1B-DPO, ep1, lr=1e-5, bs4 eff16
initial commit
Final model with checkpoints — base: OLMo-2-0425-1B-DPO, ep1, lr=1e-5, bs4 eff16
initial commit