Drop internal run names from the card

README.md

@@ -118,8 +118,7 @@ The base model's probe before training: reward 0.407, judge term 0.317, paint co
   environment and inference quota for the judge. It is not cheap.
 
 Method reproduced from [Surya Narreddi's "RL'ing Qwen to paint with
-code"](https://surya.website/rling-qwen-to-paint-with-code). Internally this run is `v22b`,
-HF job `6a95460d0718b0f6d8908805`.
+code"](https://surya.website/rling-qwen-to-paint-with-code). Trained on HF Jobs (job `6a95460d0718b0f6d8908805`).
 
 ## Where this comes from