Upload policy weights, train config and readme

README.md

@@ -5,9 +5,9 @@ license: apache-2.0
 model_name: reward_classifier
 pipeline_tag: robotics
 tags:
+- robotics
 - lerobot
 - reward_classifier
-- robotics
 ---
 
 # Model Card for reward_classifier

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ef2f59b43602300c253835f5a0dd0762a99a890926cdc7f651e0e773f8801b
+oid sha256:eec7fe990d05e17c032c0cb250f59e1af1b3c2aab73e917b572236c0a22cffe5
 size 24358564

train_config.json

@@ -4,58 +4,18 @@
         "root": null,
         "episodes": null,
         "image_transforms": {
-            "enable": false,
+            "enable": true,
             "max_num_transforms": 3,
             "random_order": false,
             "tfs": {
-                "brightness": {
+                "color_jitter": {
                     "weight": 1.0,
                     "type": "ColorJitter",
                     "kwargs": {
-                        "brightness": [
-                            0.8,
-                            1.2
-                        ]
-                    }
-                },
-                "contrast": {
-                    "weight": 1.0,
-                    "type": "ColorJitter",
-                    "kwargs": {
-                        "contrast": [
-                            0.8,
-                            1.2
-                        ]
-                    }
-                },
-                "saturation": {
-                    "weight": 1.0,
-                    "type": "ColorJitter",
-                    "kwargs": {
-                        "saturation": [
-                            0.5,
-                            1.5
-                        ]
-                    }
-                },
-                "hue": {
-                    "weight": 1.0,
-                    "type": "ColorJitter",
-                    "kwargs": {
-                        "hue": [
-                            -0.05,
-                            0.05
-                        ]
-                    }
-                },
-                "sharpness": {
-                    "weight": 1.0,
-                    "type": "SharpnessJitter",
-                    "kwargs": {
-                        "sharpness": [
-                            0.5,
-                            1.5
-                        ]
+                        "brightness": 0.2,
+                        "contrast": 0.2,
+                        "saturation": 0.2,
+                        "hue": 0.1
                     }
                 }
             }
@@ -118,7 +78,7 @@
         "weight_decay": 0.01,
         "grad_clip_norm": 1.0
     },
-    "output_dir": "outputs/train/2025-08-29/15-39-22_reward-classifier",
+    "output_dir": "outputs/train/2025-09-05/16-36-46_reward-classifier",
     "job_name": "reward-classifier",
     "resume": false,
     "seed": 2,
@@ -126,10 +86,10 @@
     "batch_size": 16,
     "steps": 5000,
     "eval_freq": 1000,
-    "log_freq": 10,
+    "log_freq": 100,
     "save_checkpoint": true,
     "save_freq": 1000,
-    "use_validation": false,
+    "use_validation": true,
     "val_split": 0.05,
     "val_freq": 10000,
     "val_batch_size": 16,
@@ -157,7 +117,7 @@
         "project": "reward-classifier",
         "entity": null,
         "notes": null,
-        "run_id": "g5irls7c",
+        "run_id": "7mcbm58f",
         "mode": null
     },
     "use_peft": false,