Update README with wandb run id 67h0ngi6

README.md

@@ -14,6 +14,7 @@ LoRA adapter (rank 32) trained with RL on a custom Opus-Magnum-style motion-plan
 
 ## Source training run
 
+- wandb: [`67h0ngi6`](https://wandb.ai/websim/opus-task/runs/67h0ngi6)
 - tinker checkpoint: `tinker://c4901d4e-3f47-5a93-a26e-af7460a95caf:train:0/sampler_weights/000045`
 - distances: 1, 2, 3, 4
 - task types: move, transmute (no bond)