model-organisms-for-real/olmo-2-0425-1b-wide-dpo-milsub-synth
Updated • 2
Note integrated DPO step_1800
Note post-hoc DPO mixed step-168
Note post-hoc DPO unmixed step-42
Note post-hoc FD mixed step-252
Note post-hoc FD unmixed step-168
Note post-hoc SDF mixed step-27
Note post-hoc SDF unmixed step-24