Add complete balanced-test metrics

README.md

@@ -15,12 +15,20 @@ This LoRA adapter uses the public RePO `XGRPOTrainer` with PolyEdit polymer refe
 It is **not** an upstream RePO checkpoint: the official repository publishes training
 code and recipes but no trained weights.
 
-Training uses all eight properties with equal property mass, only PolyEdit train
-components, Qwen2.5-3B-Instruct, four sampled generations per prompt, a verifiable reward
+Training uses all eight properties with equal property mass, 4,096 examples from only
+PolyEdit train components, 256 optimizer steps, Qwen2.5-3B-Instruct, four sampled
+generations per prompt, a verifiable reward
 combining two-anchor validity, structural locality, and a train-only property verifier,
 the reference-guidance loss, and KL regularization. Exact training and full-test metrics
 are recorded in the linked repository and `training_meta.json`.
 
+On all 8,176 balanced test requests, this adapter obtains 79.770% RDKit+TDC validity,
+51.248% two-anchor polymer validity, 33.745% changed outputs, 1.345% strict
+MIPS-retrained full-edit hits, and 0.489% observed-DFT strict full-edit hits at 24.352%
+DFT coverage. It does not outperform the polymer-adapted Molecular Optimization
+Transformer and should be treated as a reproducible RePO adaptation baseline rather than
+a claimed state-of-the-art result.
+
 Upstream RePO code: <https://github.com/tmlr-group/RePO>
 
 PolyEdit implementation and record-level evaluation: <https://github.com/promotion-kim/POLYEDIT/tree/tsyou/balanced-polymer-baseline-eval>