Add OLMo-core based DPO training module

CHANGELOG.md

@@ -4,6 +4,7 @@ All notable changes to this project will be documented in this file.
 
 
 ### Added
+- Added OLMo-core based DPO training script (https://github.com/allenai/open-instruct/pull/1391).
 - Added the ability to set active tools on a per-sample basis. See the PR for more details: https://github.com/allenai/open-instruct/pull/1382
 - Added a new changelog Github Action that makes sure you contribute to the changelog! https://github.com/allenai/open-instruct/pull/1276
 - Now, we type check `open_instruct/dataset_transformation.py` (https://github.com/allenai/open-instruct/pull/1390).

mason.py

@@ -27,6 +27,7 @@
 OPEN_INSTRUCT_COMMANDS = [
     "open_instruct/finetune.py",
     "open_instruct/dpo_tune_cache.py",
+    "open_instruct/dpo.py",
     "open_instruct/grpo_fast.py",
     "open_instruct/ppo.py",
     "open_instruct/reward_modeling.py",