Upload policy weights, train config and readme

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f9ec76d2d307d99f70226b59c7cc8980fc5fe71a7f5764c221f920ff2a48f0
+oid sha256:b7a6e456bda184efc769a41bbf4a9f33cc63ef34bbb224408dd4dd05f5769278
 size 29083940

train_config.json

@@ -125,7 +125,7 @@
             "VISUAL": "MEAN_STD"
         }
     },
-    "output_dir": "outputs/train/2025-10-19/22-50-21_reward-classifier",
+    "output_dir": "outputs/train/2025-11-02/08-55-25_reward-classifier",
     "job_name": "reward-classifier",
     "resume": false,
     "seed": 2,