diff --git a/notebooks/rlearn_evaluation.ipynb b/notebooks/rlearn_evaluation.ipynb
index ee90acc1a..8bf229108 100644
--- a/notebooks/rlearn_evaluation.ipynb
+++ b/notebooks/rlearn_evaluation.ipynb
@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -30,6 +30,14 @@
      "text": [
       "/Users/pepijnkooijmans/Documents/GitHub/lerobot\n"
      ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/pepijnkooijmans/miniconda3/envs/lerobot/lib/python3.10/site-packages/IPython/core/magics/osm.py:417: UserWarning: This is now an optional IPython functionality, setting dhist requires you to install the `pickleshare` library.\n",
+      "  self.shell.db['dhist'] = compress_dhist(dhist)[-100:]\n"
+     ]
     }
    ],
    "source": [
@@ -38,7 +46,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -50,7 +58,6 @@
     }
    ],
    "source": [
-    "import os\n",
     "import sys\n",
     "from pathlib import Path\n",
     "\n",
@@ -69,7 +76,6 @@
     "# LeRobot imports\n",
     "from lerobot.constants import OBS_IMAGES, OBS_LANGUAGE\n",
     "from lerobot.datasets.lerobot_dataset import LeRobotDataset\n",
-    "from lerobot.policies.rlearn.configuration_rlearn import RLearNConfig\n",
     "from lerobot.policies.rlearn.evaluation import (\n",
     "    RLearnEvaluator,\n",
     ")\n",
@@ -89,14 +95,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Using device: cpu\n",
+      "Using device: mps\n",
       "Loading dataset...\n",
       "Dataset loaded: 10 episodes, 1175 frames\n",
       "Features: ['observation.images.image', 'observation.state', 'action', 'timestamp', 'frame_index', 'episode_index', 'index', 'task_index', 'next.reward']\n",
@@ -107,9 +113,9 @@
    "source": [
     "# Configuration\n",
     "DATASET_REPO = \"pepijn223/rewards_bc_z3\"  # Change to your dataset\n",
-    "MODEL_PATH = \"pepijn223/rlearn_rewards_bc_z_10\"  # Change to your model checkpoint\n",
-    "DEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
-    "NUM_EVAL_EPISODES = 50  # Number of episodes for evaluation\n",
+    "MODEL_PATH = \"pepijn223/rlearn_rewards_bc_z_12\"  # Change to your model checkpoint\n",
+    "DEVICE = \"cuda\" if torch.cuda.is_available() else \"mps\"\n",
+    "NUM_EVAL_EPISODES = 10  # Number of episodes for evaluation\n",
     "\n",
     "print(f\"Using device: {DEVICE}\")\n",
     "\n",
@@ -128,7 +134,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -136,7 +142,7 @@
      "output_type": "stream",
      "text": [
       "Setting up model...\n",
-      "Loading trained model from Hugging Face Hub: pepijn223/rlearn_rewards_bc_z_10\n"
+      "Loading trained model from Hugging Face Hub: pepijn223/rlearn_rewards_bc_z_12\n"
      ]
     },
     {
@@ -151,9 +157,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "✓ Model ready on cpu\n",
-      "  Parameters: 900,447,748\n",
-      "  Trainable: 18,920,964\n"
+      "✓ Model ready on mps\n",
+      "  Parameters: 899,395,076\n",
+      "  Trainable: 17,868,292\n"
      ]
     }
    ],
@@ -183,7 +189,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -191,41 +197,46 @@
      "output_type": "stream",
      "text": [
       "Running VOC-S evaluation...\n",
-      "Evaluating VOC-S on 50 episodes...\n"
+      "Evaluating VOC-S on 10 episodes...\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Computing VOC-S: 100%|██████████| 10/10 [00:02<00:00,  3.91it/s]"
+      "Computing VOC-S:   0%|          | 0/10 [00:54<?, ?it/s]\n"
      ]
     },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "VOC-S Results:\n",
-      "  Mean correlation: 0.0000\n",
-      "  Std correlation: 0.0000\n",
-      "  IQM correlation: 0.0000\n",
-      "  Episodes evaluated: 0\n",
-      "\n",
-      "==================================================\n",
-      "VOC-S RESULTS\n",
-      "==================================================\n",
-      "Mean Correlation: 0.0000\n",
-      "Std Correlation:  0.0000\n",
-      "IQM Correlation:  0.0000\n",
-      "Episodes:         0\n",
-      "==================================================\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n"
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[9], line 6\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[38;5;66;03m# Run VOC-S evaluation\u001b[39;00m\n\u001b[1;32m      5\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRunning VOC-S evaluation...\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 6\u001b[0m voc_results \u001b[38;5;241m=\u001b[39m \u001b[43mevaluator\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mevaluate_voc_s\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      7\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdataset\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdataset\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_episodes\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mNUM_EVAL_EPISODES\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43muse_interquartile_mean\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\n\u001b[1;32m      8\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m=\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m*\u001b[39m \u001b[38;5;241m50\u001b[39m)\n\u001b[1;32m     11\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mVOC-S RESULTS\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[0;32m~/Documents/GitHub/lerobot/src/lerobot/policies/rlearn/evaluation.py:437\u001b[0m, in \u001b[0;36mRLearnEvaluator.evaluate_voc_s\u001b[0;34m(self, dataset, num_episodes, use_interquartile_mean)\u001b[0m\n\u001b[1;32m    434\u001b[0m     frames_tensor \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mstack(frames)  \u001b[38;5;66;03m# (T, C, H, W)\u001b[39;00m\n\u001b[1;32m    436\u001b[0m     \u001b[38;5;66;03m# Predict rewards\u001b[39;00m\n\u001b[0;32m--> 437\u001b[0m     episode_rewards \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict_episode_rewards\u001b[49m\u001b[43m(\u001b[49m\u001b[43mframes_tensor\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlanguage\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    438\u001b[0m     predicted_rewards\u001b[38;5;241m.\u001b[39mappend(episode_rewards)\n\u001b[1;32m    440\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/utils/_contextlib.py:116\u001b[0m, in \u001b[0;36mcontext_decorator.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    113\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m    114\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m    115\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[0;32m--> 116\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/Documents/GitHub/lerobot/src/lerobot/policies/rlearn/evaluation.py:300\u001b[0m, in \u001b[0;36mRLearnEvaluator.predict_episode_rewards\u001b[0;34m(self, frames, language, batch_size)\u001b[0m\n\u001b[1;32m    294\u001b[0m batch \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    295\u001b[0m     OBS_IMAGES: batch_sequences,  \u001b[38;5;66;03m# (B, T, C, H, W) format expected by model\u001b[39;00m\n\u001b[1;32m    296\u001b[0m     OBS_LANGUAGE: [language] \u001b[38;5;241m*\u001b[39m batch_sequences\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m    297\u001b[0m }\n\u001b[1;32m    299\u001b[0m \u001b[38;5;66;03m# Predict rewards - model returns (B, T') but we want the last timestep for each sequence\u001b[39;00m\n\u001b[0;32m--> 300\u001b[0m values \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict_rewards\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# (B, T')\u001b[39;00m\n\u001b[1;32m    302\u001b[0m \u001b[38;5;66;03m# Take the last timestep prediction for each sequence (represents current frame reward)\u001b[39;00m\n\u001b[1;32m    303\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m values\u001b[38;5;241m.\u001b[39mdim() \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m2\u001b[39m:\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/utils/_contextlib.py:116\u001b[0m, in \u001b[0;36mcontext_decorator.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    113\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m    114\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m    115\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[0;32m--> 116\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/Documents/GitHub/lerobot/src/lerobot/policies/rlearn/modeling_rlearn.py:235\u001b[0m, in \u001b[0;36mRLearNPolicy.predict_rewards\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    232\u001b[0m pixel_values \u001b[38;5;241m=\u001b[39m proc_out[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpixel_values\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mto(\u001b[38;5;28mnext\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mvision_encoder\u001b[38;5;241m.\u001b[39mparameters())\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[1;32m    234\u001b[0m \u001b[38;5;66;03m# Encode frames through visual tower per frame\u001b[39;00m\n\u001b[0;32m--> 235\u001b[0m vision_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvision_encoder\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpixel_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpixel_values\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    237\u001b[0m \u001b[38;5;66;03m# Extract CLS tokens for temporal modeling\u001b[39;00m\n\u001b[1;32m    238\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(vision_outputs, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlast_hidden_state\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py:1751\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1749\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1750\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1751\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py:1762\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1757\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1758\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1759\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1760\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1761\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1762\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1764\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1765\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/transformers/utils/generic.py:943\u001b[0m, in \u001b[0;36mcan_return_tuple.<locals>.wrapper\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    940\u001b[0m     set_attribute_for_modules(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_is_top_level_module\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m    942\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 943\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    944\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m is_requested_to_return_tuple \u001b[38;5;129;01mor\u001b[39;00m (is_configured_to_return_tuple \u001b[38;5;129;01mand\u001b[39;00m is_top_level_module):\n\u001b[1;32m    945\u001b[0m         output \u001b[38;5;241m=\u001b[39m output\u001b[38;5;241m.\u001b[39mto_tuple()\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/transformers/models/siglip/modeling_siglip.py:777\u001b[0m, in \u001b[0;36mSiglipVisionTransformer.forward\u001b[0;34m(self, pixel_values, output_attentions, output_hidden_states, interpolate_pos_encoding)\u001b[0m\n\u001b[1;32m    771\u001b[0m output_hidden_states \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    772\u001b[0m     output_hidden_states \u001b[38;5;28;01mif\u001b[39;00m output_hidden_states \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39moutput_hidden_states\n\u001b[1;32m    773\u001b[0m )\n\u001b[1;32m    775\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39membeddings(pixel_values, interpolate_pos_encoding\u001b[38;5;241m=\u001b[39minterpolate_pos_encoding)\n\u001b[0;32m--> 777\u001b[0m encoder_outputs: BaseModelOutput \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    778\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    779\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    780\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    781\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    783\u001b[0m last_hidden_state \u001b[38;5;241m=\u001b[39m encoder_outputs\u001b[38;5;241m.\u001b[39mlast_hidden_state\n\u001b[1;32m    784\u001b[0m last_hidden_state \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpost_layernorm(last_hidden_state)\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py:1751\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1749\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1750\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1751\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py:1762\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1757\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1758\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1759\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1760\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1761\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1762\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1764\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1765\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/transformers/utils/generic.py:943\u001b[0m, in \u001b[0;36mcan_return_tuple.<locals>.wrapper\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    940\u001b[0m     set_attribute_for_modules(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_is_top_level_module\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m    942\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 943\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    944\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m is_requested_to_return_tuple \u001b[38;5;129;01mor\u001b[39;00m (is_configured_to_return_tuple \u001b[38;5;129;01mand\u001b[39;00m is_top_level_module):\n\u001b[1;32m    945\u001b[0m         output \u001b[38;5;241m=\u001b[39m output\u001b[38;5;241m.\u001b[39mto_tuple()\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/transformers/models/siglip/modeling_siglip.py:608\u001b[0m, in \u001b[0;36mSiglipEncoder.forward\u001b[0;34m(self, inputs_embeds, attention_mask, output_attentions, output_hidden_states)\u001b[0m\n\u001b[1;32m    605\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m output_hidden_states:\n\u001b[1;32m    606\u001b[0m     encoder_states \u001b[38;5;241m=\u001b[39m encoder_states \u001b[38;5;241m+\u001b[39m (hidden_states,)\n\u001b[0;32m--> 608\u001b[0m layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[43mencoder_layer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    609\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    610\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    611\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    612\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    614\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m layer_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m    616\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m output_attentions:\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/transformers/modeling_layers.py:83\u001b[0m, in \u001b[0;36mGradientCheckpointingLayer.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m     80\u001b[0m         logger\u001b[38;5;241m.\u001b[39mwarning(message)\n\u001b[1;32m     82\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gradient_checkpointing_func(partial(\u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs), \u001b[38;5;241m*\u001b[39margs)\n\u001b[0;32m---> 83\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py:1751\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1749\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1750\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1751\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py:1762\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1757\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1758\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1759\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1760\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1761\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1762\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1764\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1765\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/transformers/models/siglip/modeling_siglip.py:463\u001b[0m, in \u001b[0;36mSiglipEncoderLayer.forward\u001b[0;34m(self, hidden_states, attention_mask, output_attentions)\u001b[0m\n\u001b[1;32m    460\u001b[0m residual \u001b[38;5;241m=\u001b[39m hidden_states\n\u001b[1;32m    462\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlayer_norm1(hidden_states)\n\u001b[0;32m--> 463\u001b[0m hidden_states, attn_weights \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mself_attn\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    464\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    465\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    466\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    467\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    468\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m residual \u001b[38;5;241m+\u001b[39m hidden_states\n\u001b[1;32m    470\u001b[0m residual \u001b[38;5;241m=\u001b[39m hidden_states\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py:1751\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1749\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1750\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1751\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/torch/nn/modules/module.py:1762\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1757\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1758\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1759\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1760\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1761\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1762\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1764\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1765\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/transformers/models/siglip/modeling_siglip.py:399\u001b[0m, in \u001b[0;36mSiglipAttention.forward\u001b[0;34m(self, hidden_states, attention_mask, output_attentions)\u001b[0m\n\u001b[1;32m    396\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    397\u001b[0m         attention_interface \u001b[38;5;241m=\u001b[39m ALL_ATTENTION_FUNCTIONS[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39m_attn_implementation]\n\u001b[0;32m--> 399\u001b[0m attn_output, attn_weights \u001b[38;5;241m=\u001b[39m \u001b[43mattention_interface\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    400\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    401\u001b[0m \u001b[43m    \u001b[49m\u001b[43mqueries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    402\u001b[0m \u001b[43m    \u001b[49m\u001b[43mkeys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    403\u001b[0m \u001b[43m    \u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    404\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    405\u001b[0m \u001b[43m    \u001b[49m\u001b[43mis_causal\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mis_causal\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    406\u001b[0m \u001b[43m    \u001b[49m\u001b[43mscaling\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscale\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    407\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdropout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.0\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtraining\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdropout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    408\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    410\u001b[0m attn_output \u001b[38;5;241m=\u001b[39m attn_output\u001b[38;5;241m.\u001b[39mreshape(batch_size, seq_length, embed_dim)\u001b[38;5;241m.\u001b[39mcontiguous()\n\u001b[1;32m    411\u001b[0m attn_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mout_proj(attn_output)\n",
+      "File \u001b[0;32m~/miniconda3/envs/lerobot/lib/python3.10/site-packages/transformers/integrations/sdpa_attention.py:66\u001b[0m, in \u001b[0;36msdpa_attention_forward\u001b[0;34m(module, query, key, value, attention_mask, dropout, scaling, is_causal, **kwargs)\u001b[0m\n\u001b[1;32m     63\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mjit\u001b[38;5;241m.\u001b[39mis_tracing() \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(is_causal, torch\u001b[38;5;241m.\u001b[39mTensor):\n\u001b[1;32m     64\u001b[0m     is_causal \u001b[38;5;241m=\u001b[39m is_causal\u001b[38;5;241m.\u001b[39mitem()\n\u001b[0;32m---> 66\u001b[0m attn_output \u001b[38;5;241m=\u001b[39m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mnn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunctional\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscaled_dot_product_attention\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     67\u001b[0m \u001b[43m    \u001b[49m\u001b[43mquery\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     68\u001b[0m \u001b[43m    \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     69\u001b[0m \u001b[43m    \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     70\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattn_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     71\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdropout_p\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdropout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     72\u001b[0m \u001b[43m    \u001b[49m\u001b[43mscale\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mscaling\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     73\u001b[0m \u001b[43m    \u001b[49m\u001b[43mis_causal\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mis_causal\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     74\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     75\u001b[0m attn_output \u001b[38;5;241m=\u001b[39m attn_output\u001b[38;5;241m.\u001b[39mtranspose(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m2\u001b[39m)\u001b[38;5;241m.\u001b[39mcontiguous()\n\u001b[1;32m     77\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m attn_output, \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
      ]
     }
    ],
@@ -258,7 +269,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -270,7 +281,7 @@
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 1600x1200 with 4 Axes>"
       ]
@@ -284,35 +295,7 @@
      "text": [
       "\n",
       "Detailed Episode Statistics:\n",
-      "================================================================================\n",
-      "Episode 0:\n",
-      "  Language: place the white sponge in the ceramic bowl\n",
-      "  Frames: 32\n",
-      "  VOC-S (Spearman ρ): -0.1635 (p=0.3713)\n",
-      "  Reward range: [-0.010, 0.068]\n",
-      "  Trend: ↘ Decreasing\n",
-      "--------------------------------------------------------------------------------\n",
-      "Episode 1:\n",
-      "  Language: move the arm in a circular motion\n",
-      "  Frames: 32\n",
-      "  VOC-S (Spearman ρ): 0.1312 (p=0.4740)\n",
-      "  Reward range: [-0.010, 0.070]\n",
-      "  Trend: ↗ Increasing\n",
-      "--------------------------------------------------------------------------------\n",
-      "Episode 2:\n",
-      "  Language: place the bottle in the ceramic bowl\n",
-      "  Frames: 32\n",
-      "  VOC-S (Spearman ρ): -0.1628 (p=0.3735)\n",
-      "  Reward range: [-0.010, 0.067]\n",
-      "  Trend: ↘ Decreasing\n",
-      "--------------------------------------------------------------------------------\n",
-      "Episode 3:\n",
-      "  Language: drag the ceramic bowl in a circle\n",
-      "  Frames: 2\n",
-      "  VOC-S (Spearman ρ): -1.0000 (p=nan)\n",
-      "  Reward range: [-0.008, 0.076]\n",
-      "  Trend: ↘ Decreasing\n",
-      "--------------------------------------------------------------------------------\n"
+      "================================================================================\n"
      ]
     }
    ],
diff --git a/src/lerobot/datasets/factory.py b/src/lerobot/datasets/factory.py
index 50c158f8f..f233feeb0 100644
--- a/src/lerobot/datasets/factory.py
+++ b/src/lerobot/datasets/factory.py
@@ -13,7 +13,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-import logging
 from pprint import pformat
 
 import torch
@@ -87,7 +86,7 @@ def make_dataset(cfg: TrainPipelineConfig) -> LeRobotDataset | MultiLeRobotDatas
             cfg.dataset.repo_id, root=cfg.dataset.root, revision=cfg.dataset.revision
         )
         delta_timestamps = resolve_delta_timestamps(cfg.policy, ds_meta)
-        
+
         # Handle percentage parameter
         episodes = cfg.dataset.episodes
         if cfg.dataset.percentage is not None:
@@ -96,8 +95,11 @@ def make_dataset(cfg: TrainPipelineConfig) -> LeRobotDataset | MultiLeRobotDatas
             num_episodes_to_use = max(1, int(total_episodes * cfg.dataset.percentage / 100))
             episodes = list(range(num_episodes_to_use))
             import logging
-            logging.info(f"Using {cfg.dataset.percentage}% of dataset: {num_episodes_to_use}/{total_episodes} episodes")
-        
+
+            logging.info(
+                f"Using {cfg.dataset.percentage}% of dataset: {num_episodes_to_use}/{total_episodes} episodes"
+            )
+
         dataset = LeRobotDataset(
             cfg.dataset.repo_id,
             root=cfg.dataset.root,
diff --git a/src/lerobot/policies/__init__.py b/src/lerobot/policies/__init__.py
index 3c3b2b7d8..7ddb17705 100644
--- a/src/lerobot/policies/__init__.py
+++ b/src/lerobot/policies/__init__.py
@@ -16,11 +16,11 @@ from .act.configuration_act import ACTConfig as ACTConfig
 from .diffusion.configuration_diffusion import DiffusionConfig as DiffusionConfig
 from .pi0.configuration_pi0 import PI0Config as PI0Config
 from .pi0.processor_pi0 import Pi0NewLineProcessor
+from .rlearn.configuration_rlearn import RLearNConfig as RLearNConfig
 from .smolvla.configuration_smolvla import SmolVLAConfig as SmolVLAConfig
 from .smolvla.processor_smolvla import SmolVLANewLineProcessor
 from .tdmpc.configuration_tdmpc import TDMPCConfig as TDMPCConfig
 from .vqbet.configuration_vqbet import VQBeTConfig as VQBeTConfig
-from .rlearn.configuration_rlearn import RLearNConfig as RLearNConfig
 
 __all__ = [
     "ACTConfig",
diff --git a/src/lerobot/policies/factory.py b/src/lerobot/policies/factory.py
index 1af9b728b..d1e911e19 100644
--- a/src/lerobot/policies/factory.py
+++ b/src/lerobot/policies/factory.py
@@ -301,7 +301,7 @@ def make_policy(
     cfg.output_features = {key: ft for key, ft in features.items() if ft.type is FeatureType.ACTION}
     cfg.input_features = {key: ft for key, ft in features.items() if key not in cfg.output_features}
     kwargs["config"] = cfg
-    
+
     # Pass episode_data_index for RLearN policy to calculate proper progress
     if cfg.type == "rlearn" and episode_data_index is not None:
         kwargs["episode_data_index"] = episode_data_index
diff --git a/src/lerobot/policies/rlearn/configuration_rlearn.py b/src/lerobot/policies/rlearn/configuration_rlearn.py
index cd5bad7f5..2d04f0b4f 100644
--- a/src/lerobot/policies/rlearn/configuration_rlearn.py
+++ b/src/lerobot/policies/rlearn/configuration_rlearn.py
@@ -38,7 +38,7 @@ class RLearNConfig(PreTrainedConfig):
     """
 
     # Encoders
-    model_name: str = "google/siglip2-large-patch16-256"
+    model_name: str = "google/siglip2-base-patch16-256"
     freeze_backbones: bool = True
 
     # Temporal aggregator
@@ -61,12 +61,12 @@ class RLearNConfig(PreTrainedConfig):
     # Training
     learning_rate: float = 1e-4
     weight_decay: float = 0.01
-    
+
     # ReWiND-specific parameters
     use_video_rewind: bool = True  # Enable video rewinding augmentation
     rewind_prob: float = 0.5  # Probability of applying rewind to each batch
     use_mismatch_loss: bool = True  # Enable mismatched language-video loss
-    
+
     # Loss hyperparameters (simplified for ReWiND)
     # The main loss is just MSE between predicted and target progress
 
diff --git a/src/lerobot/policies/rlearn/evaluation.py b/src/lerobot/policies/rlearn/evaluation.py
index cd4909763..13f44e7cf 100644
--- a/src/lerobot/policies/rlearn/evaluation.py
+++ b/src/lerobot/policies/rlearn/evaluation.py
@@ -242,6 +242,9 @@ class RLearnEvaluator:
     def predict_episode_rewards(self, frames: Tensor, language: str, batch_size: int = 16) -> np.ndarray:
         """
         Predict rewards for a single episode using proper temporal sequences.
+        
+        Note: With ReWiND loss, the model predicts progress values (0-1) across episodes,
+        which serve as dense reward signals for policy learning.
 
         Args:
             frames: Video frames tensor of shape (T, C, H, W)
@@ -249,7 +252,7 @@ class RLearnEvaluator:
             batch_size: Maximum number of temporal sequences to process at once
 
         Returns:
-            Predicted rewards array of shape (T,)
+            Predicted progress/rewards array of shape (T,) with values typically in [0, 1]
         """
         T = frames.shape[0]
         max_seq_len = self.model.config.max_seq_len
@@ -260,7 +263,7 @@ class RLearnEvaluator:
         # Create temporal sequences for each frame
         # For frame i, we want frames [i-max_seq_len+1, ..., i-1, i]
         temporal_sequences = []
-        
+
         for i in range(T):
             # Create sequence ending at frame i
             seq_frames = []
@@ -268,14 +271,14 @@ class RLearnEvaluator:
                 # Use frame j if available, otherwise repeat the first available frame
                 frame_idx = max(0, min(j, T - 1))
                 seq_frames.append(processed_frames[frame_idx])
-            
+
             # Pad sequence to max_seq_len by repeating the first frame if needed
             while len(seq_frames) < max_seq_len:
                 seq_frames.insert(0, seq_frames[0])  # Prepend first frame
-            
+
             # Take only the last max_seq_len frames if we have too many
             seq_frames = seq_frames[-max_seq_len:]
-            
+
             temporal_sequences.append(torch.stack(seq_frames))  # (max_seq_len, C, H, W)
 
         # Stack all temporal sequences: (T, max_seq_len, C, H, W)
@@ -286,7 +289,7 @@ class RLearnEvaluator:
         for i in range(0, T, batch_size):
             end_idx = min(i + batch_size, T)
             batch_sequences = all_sequences[i:end_idx].to(self.device)  # (B, max_seq_len, C, H, W)
-            
+
             # Create batch for model
             batch = {
                 OBS_IMAGES: batch_sequences,  # (B, T, C, H, W) format expected by model
@@ -295,13 +298,13 @@ class RLearnEvaluator:
 
             # Predict rewards - model returns (B, T') but we want the last timestep for each sequence
             values = self.model.predict_rewards(batch)  # (B, T')
-            
+
             # Take the last timestep prediction for each sequence (represents current frame reward)
             if values.dim() == 2:
                 batch_rewards = values[:, -1].cpu().numpy()  # (B,) - last timestep
             else:
                 batch_rewards = values.cpu().numpy()  # (B,) - already single timestep
-            
+
             rewards.extend(batch_rewards)
 
         return np.array(rewards[:T])  # Ensure exact length
@@ -570,6 +573,83 @@ class RLearnEvaluator:
 
         return detection_results
 
+    def evaluate_rewind_progress(
+        self, dataset, num_episodes: int = 100
+    ) -> dict[str, Any]:
+        """
+        Evaluate ReWiND-specific progress properties.
+        
+        Checks:
+        1. Progress values are in [0, 1] range
+        2. Progress increases monotonically (or mostly)
+        3. First frames have low progress, last frames have high progress
+        """
+        episodes = np.random.choice(len(dataset.meta.episodes), min(num_episodes, len(dataset.meta.episodes)), replace=False)
+        
+        results = {
+            "progress_range_violations": 0,
+            "monotonicity_scores": [],
+            "start_progress_values": [],
+            "end_progress_values": [],
+            "episodes_evaluated": 0
+        }
+        
+        for ep_idx in episodes:
+            try:
+                # Get episode data
+                ep_start = dataset.episode_data_index["from"][ep_idx].item()
+                ep_end = dataset.episode_data_index["to"][ep_idx].item()
+                
+                # Sample some frames from episode
+                sample_indices = np.linspace(ep_start, ep_end-1, min(20, ep_end-ep_start), dtype=int)
+                
+                frames = []
+                for idx in sample_indices:
+                    item = dataset[idx]
+                    if OBS_IMAGES in item:
+                        frames.append(item[OBS_IMAGES])
+                    elif OBS_IMAGE in item:
+                        frames.append(item[OBS_IMAGE])
+                    else:
+                        continue
+                
+                if len(frames) < 2:
+                    continue
+                    
+                frames = torch.stack(frames)
+                language = dataset[ep_start].get("task", "")
+                
+                # Predict rewards/progress
+                progress = self.predict_episode_rewards(frames, language)
+                
+                # Check range violations
+                range_violations = np.sum((progress < 0) | (progress > 1))
+                results["progress_range_violations"] += range_violations
+                
+                # Check monotonicity (should generally increase)
+                if len(progress) > 1:
+                    diffs = np.diff(progress)
+                    monotonicity = np.mean(diffs >= 0)  # Fraction of non-decreasing steps
+                    results["monotonicity_scores"].append(monotonicity)
+                
+                # Record start/end values
+                results["start_progress_values"].append(progress[0])
+                results["end_progress_values"].append(progress[-1])
+                results["episodes_evaluated"] += 1
+                
+            except Exception as e:
+                print(f"Error evaluating episode {ep_idx}: {e}")
+                continue
+        
+        # Summarize results
+        if results["episodes_evaluated"] > 0:
+            results["mean_monotonicity"] = np.mean(results["monotonicity_scores"])
+            results["mean_start_progress"] = np.mean(results["start_progress_values"])
+            results["mean_end_progress"] = np.mean(results["end_progress_values"])
+            results["progress_increase"] = results["mean_end_progress"] - results["mean_start_progress"]
+        
+        return results
+
     def comprehensive_evaluation(
         self,
         dataset,
diff --git a/src/lerobot/policies/rlearn/modeling_rlearn.py b/src/lerobot/policies/rlearn/modeling_rlearn.py
index cd41968a9..0bc7068a5 100644
--- a/src/lerobot/policies/rlearn/modeling_rlearn.py
+++ b/src/lerobot/policies/rlearn/modeling_rlearn.py
@@ -35,7 +35,7 @@ High-level Architecture
   +------------------------------+
   |  Vision Encoder (frozen)     |  e.g. SigLIP2 vision tower
   +------------------------------+
-        |
+        |s
         |  pooled per-frame embeddings (BT, H_v)
         v
   reshape -> (B, T, H_v) -- Linear proj --> (B, T, D)
@@ -214,7 +214,7 @@ class RLearNPolicy(PreTrainedPolicy):
         )
         lang_emb = self.text_proj(lang_emb)  # (B, D)
 
-        # ---- NEW: use the HF processor to standardize size & normalization ----
+        # Use the HF processor to standardize size & normalization
         # Flatten (B, T_eff, C, H, W) -> (BT, C, H, W)
         BT = B * T_eff
         flat = frames.reshape(BT, C, H, W).detach().cpu()
@@ -230,7 +230,6 @@ class RLearNPolicy(PreTrainedPolicy):
 
         proc_out = self.processor(images=images, return_tensors="pt")
         pixel_values = proc_out["pixel_values"].to(next(self.vision_encoder.parameters()).device)
-        # ----------------------------------------------------------------------
 
         # Encode frames through visual tower per frame
         vision_outputs = self.vision_encoder(pixel_values=pixel_values)
@@ -276,7 +275,7 @@ class RLearNPolicy(PreTrainedPolicy):
         Expected batch keys:
           - OBS_IMAGES: list[Tensor] of shape [(B, C, H, W), ...] per time step or stacked (B, T, C, H, W)
           - OBS_LANGUAGE: optional string tokens already tokenized externally or raw strings
-          
+
         Note: Progress labels (0 to 1) are generated automatically for each episode.
               No REWARD key is needed in the batch.
         """
@@ -362,42 +361,42 @@ class RLearNPolicy(PreTrainedPolicy):
         # Generate progress labels on-the-fly (ReWiND approach)
         # IMPORTANT: Progress should be 0-1 across the ENTIRE EPISODE, not just the temporal window
         loss_dict: dict[str, float] = {}
-        
+
         # Check if video rewinding already set the target
-        if self.training and self.config.use_video_rewind and 'augmented_target' in locals():
+        if self.training and self.config.use_video_rewind and "augmented_target" in locals():
             # Use the augmented target from video rewinding
             target = augmented_target
         else:
             # Calculate true episode progress using episode_index and frame_index from batch
-            if "episode_index" in batch and "frame_index" in batch and hasattr(self, 'episode_data_index'):
+            if "episode_index" in batch and "frame_index" in batch and hasattr(self, "episode_data_index"):
                 # Get episode indices and frame indices from batch
                 episode_indices = batch["episode_index"]  # Shape: (B,)
                 frame_indices = batch["frame_index"]  # Shape: (B,)
-                
+
                 # Calculate progress for the current frame in each sample
                 progress_values = []
-                
+
                 for b_idx in range(B):
                     ep_idx = episode_indices[b_idx].item()
                     frame_idx = frame_indices[b_idx].item()
-                    
+
                     # Get episode boundaries
                     ep_start = self.episode_data_index["from"][ep_idx].item()
                     ep_end = self.episode_data_index["to"][ep_idx].item()
                     ep_length = ep_end - ep_start
-                    
+
                     # Progress from 0 to 1 within the episode
                     # frame_index is relative to the episode (0-based within episode)
                     progress = frame_idx / max(1, ep_length - 1)
                     progress_values.append(progress)
-                
+
                 # Create progress tensor for the current frame (last in temporal sequence)
                 current_progress = torch.tensor(progress_values, device=values.device, dtype=values.dtype)
-                
+
                 # Now calculate progress for ALL frames in the temporal window
                 # The observation_delta_indices tell us which frames we're looking at
                 delta_indices = self.config.observation_delta_indices  # e.g., [-15, -14, ..., 0]
-                
+
                 # Calculate progress for each frame in the temporal window
                 all_progress = []
                 for delta in delta_indices:
@@ -406,42 +405,44 @@ class RLearNPolicy(PreTrainedPolicy):
                     for b_idx in range(B):
                         ep_idx = episode_indices[b_idx].item()
                         frame_idx = frame_indices[b_idx].item()
-                        
+
                         # Calculate the actual frame index with delta
                         target_frame_idx = frame_idx + delta
-                        
+
                         # Get episode boundaries
                         ep_start = self.episode_data_index["from"][ep_idx].item()
                         ep_end = self.episode_data_index["to"][ep_idx].item()
                         ep_length = ep_end - ep_start
-                        
+
                         # Clamp to episode boundaries (frame_index is relative to episode)
                         target_frame_idx = max(0, min(ep_length - 1, target_frame_idx))
-                        
+
                         # Calculate progress for this frame
                         prog = target_frame_idx / max(1, ep_length - 1)
                         frame_progress.append(prog)
-                    
-                    all_progress.append(torch.tensor(frame_progress, device=values.device, dtype=values.dtype))
-                
+
+                    all_progress.append(
+                        torch.tensor(frame_progress, device=values.device, dtype=values.dtype)
+                    )
+
                 # Stack to get (B, T) tensor where T is the temporal sequence length
                 target = torch.stack(all_progress, dim=1)  # (B, max_seq_len)
-                
+
                 # Apply stride/dropout indexing to match the processed frames
                 target = target[:, idx]
-                
-            elif "index" in batch and hasattr(self, 'episode_data_index'):
+
+            elif "index" in batch and hasattr(self, "episode_data_index"):
                 # Fallback: Use global index if available
                 global_indices = batch["index"]  # Shape: (B,)
-                
+
                 # For each index, find which episode it belongs to and its position
                 progress_values = []
-                
+
                 for global_idx in global_indices:
                     # Find which episode this index belongs to
                     episode_starts = self.episode_data_index["from"]
                     episode_ends = self.episode_data_index["to"]
-                    
+
                     # Find the episode by checking which range the index falls into
                     episode_idx = None
                     frame_in_episode = None
@@ -450,30 +451,32 @@ class RLearNPolicy(PreTrainedPolicy):
                             episode_idx = ep_idx
                             frame_in_episode = global_idx.item() - episode_starts[ep_idx].item()
                             break
-                    
+
                     if episode_idx is not None:
                         # Calculate position within episode
                         ep_start = episode_starts[episode_idx].item()
                         ep_end = episode_ends[episode_idx].item()
                         ep_length = ep_end - ep_start
-                        
+
                         # Progress from 0 to 1 within the episode
                         progress = frame_in_episode / max(1, ep_length - 1)
                     else:
                         # Fallback if we can't find the episode (shouldn't happen)
                         progress = 0.5
-                    
+
                     progress_values.append(progress)
-                
+
                 # For temporal window, use simplified linear progress
                 # (proper calculation would need all frame indices in the window)
                 T_effective = len(idx)
                 target = torch.tensor(progress_values, device=values.device, dtype=values.dtype)
                 target = target.unsqueeze(1).expand(B, T_effective)  # Simple expansion
-                
+
             else:
-                raise ValueError("No episode information found in batch. Please ensure 'episode_index' and 'frame_index' keys are present.")
-            
+                raise ValueError(
+                    "No episode information found in batch. Please ensure 'episode_index' and 'frame_index' keys are present."
+                )
+
         # During inference, we might not want to compute loss
         if not self.training and target is None:
             loss = values.mean() * 0.0
@@ -482,25 +485,25 @@ class RLearNPolicy(PreTrainedPolicy):
 
         # ReWiND Loss (following the paper exactly)
         # The core loss is progress regression with video rewinding augmentation
-        
+
         # 1) Main progress regression loss for matched sequences
         # Target should be normalized progress from 0 to 1 (t/T)
         L_progress = F.mse_loss(values, target)
-        
+
         # 2) Mismatched video-language pairs should predict zero progress
         L_mismatch = torch.zeros((), device=values.device)
         if self.training and self.config.use_mismatch_loss and values.size(0) > 1:
             # Randomly shuffle language instructions within the batch
             shuffled_indices = torch.randperm(B, device=values.device)
             lang_mismatch = lang_emb[shuffled_indices]
-            
+
             # Forward pass with mismatched language
             mismatch_feat = self.temporal(visual_seq, lang_mismatch, return_features=True)
             mismatch_values = self.head(mismatch_feat).squeeze(-1)
-            
+
             # Mismatched pairs should predict zero progress
             L_mismatch = F.mse_loss(mismatch_values, torch.zeros_like(target))
-        
+
         # Total loss is just progress regression (rewinding is handled via data augmentation)
         loss = L_progress + L_mismatch
 
@@ -720,7 +723,7 @@ def encode_language(
 
 def apply_video_rewind(frames: Tensor, rewind_prob: float = 0.5) -> tuple[Tensor, Tensor]:
     """Apply video rewinding augmentation as described in ReWiND paper.
-    
+
     Each video in the batch has an independent chance of being rewound.
 
     Args:
@@ -732,61 +735,61 @@ def apply_video_rewind(frames: Tensor, rewind_prob: float = 0.5) -> tuple[Tensor
     """
     B, T, C, H, W = frames.shape
     device = frames.device
-    
+
     # Create default progress labels (linearly increasing from 0 to 1)
     default_progress = torch.linspace(0, 1, T, device=device).unsqueeze(0).expand(B, -1)
-    
+
     # Apply rewind augmentation to each sample in batch independently
     augmented_frames = []
     augmented_progress = []
-    
+
     for b in range(B):
         # Each video has independent chance of being rewound
         should_rewind = torch.rand(1).item() < rewind_prob
-        
+
         if not should_rewind or T < 3:
             # Keep original sequence
             augmented_frames.append(frames[b])
             augmented_progress.append(default_progress[b])
             continue
-            
+
         # Apply rewinding to this video
         # Split point i: between frame 2 and T-1
         i = torch.randint(2, T, (1,)).item()
-        
+
         # Rewind length k: between 1 and i-1 frames
         k = torch.randint(1, min(i, T - i + 1), (1,)).item()
-        
+
         # Create rewound sequence: o1...oi, oi-1, ..., oi-k
         forward_frames = frames[b, :i]  # Frames up to split point
-        reverse_frames = frames[b, max(0, i-k):i].flip(dims=[0])  # Reversed frames
-        
+        reverse_frames = frames[b, max(0, i - k) : i].flip(dims=[0])  # Reversed frames
+
         # Concatenate forward and reverse parts
         rewound_seq = torch.cat([forward_frames, reverse_frames], dim=0)
-        
+
         # Pad with zeros if needed to maintain shape
         if rewound_seq.shape[0] < T:
             padding = torch.zeros(T - rewound_seq.shape[0], C, H, W, device=device)
             rewound_seq = torch.cat([rewound_seq, padding], dim=0)
         elif rewound_seq.shape[0] > T:
             rewound_seq = rewound_seq[:T]
-        
+
         # Create corresponding progress labels
         # Forward part: increasing progress
-        forward_progress = torch.linspace(0, i/T, i, device=device)
-        # Reverse part: decreasing progress  
-        reverse_progress = torch.linspace(i/T, max(0, (i-k)/T), k, device=device)
-        
+        forward_progress = torch.linspace(0, i / T, i, device=device)
+        # Reverse part: decreasing progress
+        reverse_progress = torch.linspace(i / T, max(0, (i - k) / T), k, device=device)
+
         rewound_progress = torch.cat([forward_progress, reverse_progress])
-        
+
         # Pad progress if needed
         if rewound_progress.shape[0] < T:
             padding = torch.zeros(T - rewound_progress.shape[0], device=device)
             rewound_progress = torch.cat([rewound_progress, padding])
         elif rewound_progress.shape[0] > T:
             rewound_progress = rewound_progress[:T]
-            
+
         augmented_frames.append(rewound_seq)
         augmented_progress.append(rewound_progress)
-    
+
     return torch.stack(augmented_frames), torch.stack(augmented_progress)
diff --git a/src/lerobot/policies/rlearn/rlearn_plan.md b/src/lerobot/policies/rlearn/rlearn_plan.md
index ba02ed982..4c1648adb 100644
--- a/src/lerobot/policies/rlearn/rlearn_plan.md
+++ b/src/lerobot/policies/rlearn/rlearn_plan.md
@@ -125,18 +125,18 @@ Default weights: $\lambda_{\text{prog}}=1.0$, $\lambda_{\text{spatial-nce}}=0.5$
 - Do first training [x]
 - Implement on-the-fly progress label generation (no need for pre-annotated rewards) [x]
 - Try different losses
-  - Only rewind loss  [x]
-  - Convert python -m lerobot.datasets.v21.convert_dataset_v20_to_v21 --repo-id=IPEC-COMMUNITY/bc_z_lerobot
+  - Only rewind loss [x]
   - Test only rewind loss (evaluate) []
   - Check rewind implementatyion by hand []
   - Only vlc loss then eval []
   - Vlc + rewind loss then eval []
 - Cleanup code []
+- Convert python -m lerobot.datasets.v21.convert_dataset_v20_to_v21 --repo-id=IPEC-COMMUNITY/bc_z_lerobot and train on 1 percent
+- Then on 10 percent
 - Try DINO v3 as encoder Base 86 M: https://huggingface.co/facebook/dinov3-vitb16-pretrain-lvd1689m with HuggingFaceTB/SmolLM2-135M-Instruct ? []
 - Add more artificial text to dataset generated by vlm (google gemini) []
   - See google gemini vlm caption [] https://gemini.google.com/app/7e332ffaf32580f2
   - Multiple captions per video, creat method to generate as much data as possible etc [] https://arxiv.org/abs/2508.13446, https://arxiv.org/pdf/2412.04453
 - How can we improve spatial aware learning? co generating captions for each frame with language decoder?
-- Add droid []
 - Extend evaluation []
-- Add other dataset mentioned above []
+- Add other datasets mentioned above []
diff --git a/src/lerobot/scripts/train.py b/src/lerobot/scripts/train.py
index cafa860b7..601b15f48 100644
--- a/src/lerobot/scripts/train.py
+++ b/src/lerobot/scripts/train.py
@@ -137,7 +137,7 @@ def train(cfg: TrainPipelineConfig):
 
     logging.info("Creating policy")
     # Pass episode_data_index for RLearN to calculate proper progress
-    episode_data_index = dataset.episode_data_index if hasattr(dataset, 'episode_data_index') else None
+    episode_data_index = dataset.episode_data_index if hasattr(dataset, "episode_data_index") else None
     policy = make_policy(
         cfg=cfg.policy,
         ds_meta=dataset.meta,
diff --git a/tests/policies/rlearn/test_temporal_evaluation.py b/tests/policies/rlearn/test_temporal_evaluation.py
index 470242770..c88832a18 100644
--- a/tests/policies/rlearn/test_temporal_evaluation.py
+++ b/tests/policies/rlearn/test_temporal_evaluation.py
@@ -1,57 +1,57 @@
 #!/usr/bin/env python
 
 import torch
-import numpy as np
+
 from lerobot.policies.rlearn.configuration_rlearn import RLearNConfig
-from lerobot.policies.rlearn.modeling_rlearn import RLearNPolicy
 from lerobot.policies.rlearn.evaluation import RLearnEvaluator
+from lerobot.policies.rlearn.modeling_rlearn import RLearNPolicy
 
 
 def test_temporal_evaluation():
     """Test that evaluation creates proper temporal sequences with past frames."""
-    
+
     # Create a simple config
     config = RLearNConfig(
         max_seq_len=4,  # Small for testing
-        dim_model=64,   # Small for testing
+        dim_model=64,  # Small for testing
         n_heads=2,
         n_layers=2,
     )
-    
+
     # Create model (will be randomly initialized)
     model = RLearNPolicy(config)
     model.eval()
-    
+
     # Create evaluator
     evaluator = RLearnEvaluator(model, device="cpu")
-    
+
     # Create test episode: 8 frames of 3x64x64 images
     T, C, H, W = 8, 3, 64, 64
     frames = torch.randn(T, C, H, W)
     language = "test instruction"
-    
+
     print(f"Input episode shape: {frames.shape}")
     print(f"Model expects sequences of length: {config.max_seq_len}")
-    
+
     # Test the evaluation
     rewards = evaluator.predict_episode_rewards(frames, language, batch_size=4)
-    
+
     print(f"Output rewards shape: {rewards.shape}")
     print(f"Rewards: {rewards}")
-    
+
     # Verify we get one reward per frame
     assert len(rewards) == T, f"Expected {T} rewards, got {len(rewards)}"
-    
+
     print("✅ Test passed! Evaluation correctly processes temporal sequences.")
-    
+
     # Test with very short episode (shorter than max_seq_len)
     short_frames = torch.randn(2, C, H, W)  # Only 2 frames
     short_rewards = evaluator.predict_episode_rewards(short_frames, language)
-    
+
     print(f"\nShort episode shape: {short_frames.shape}")
     print(f"Short rewards shape: {short_rewards.shape}")
     assert len(short_rewards) == 2, f"Expected 2 rewards, got {len(short_rewards)}"
-    
+
     print("✅ Short episode test passed!")