Upload policy weights, train config and readme

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2586745acf1d06c4785dcbfdee94dfd46f75f54589f9737e795c3db20a2806
+oid sha256:88f467dcce0499ebc3571939c40b3c056a8d366947e9fdf42a5c2b618a76522b
 size 29083980

train_config.json

@@ -133,13 +133,13 @@
             "VISUAL": "MEAN_STD"
         }
     },
-    "output_dir": "outputs/train/2025-11-25/15-59-21_reward-classifier",
+    "output_dir": "outputs/train/2025-12-02/11-57-11_reward-classifier",
     "job_name": "reward-classifier",
     "resume": false,
     "seed": 2,
     "num_workers": 4,
     "batch_size": 16,
-    "steps": 50000,
+    "steps": 80000,
     "eval_freq": 2000,
     "log_freq": 100,
     "save_checkpoint": true,