diff --git a/docs/readthedocs/source/doc/Chronos/Howto/how_to_train_forecaster_on_one_node.ipynb b/docs/readthedocs/source/doc/Chronos/Howto/how_to_train_forecaster_on_one_node.ipynb
index 1a9351c9bbf..3af545fa532 100644
--- a/docs/readthedocs/source/doc/Chronos/Howto/how_to_train_forecaster_on_one_node.ipynb
+++ b/docs/readthedocs/source/doc/Chronos/Howto/how_to_train_forecaster_on_one_node.ipynb
@@ -108,7 +108,7 @@
     "train_data = tsdata_train\n",
     "\n",
     "# uncomment this line to change `train_data` as pytorch dataloader\n",
-    "# train_data = tsdata_train.to_torch_data_loader(roll=True, lookback=48, horizon=1)\n",
+    "# train_data = tsdata_train.to_torch_data_loader(lookback=48, horizon=1)\n",
     "\n",
     "# uncomment this line to change `train_data` as numpy ndarray\n",
     "# train_data = tsdata_train.roll(lookback=48, horizon=1).to_numpy()"
@@ -185,7 +185,7 @@
    "outputs": [],
    "source": [
     "# comment this line if you want to try other formats\n",
-    "val_data = tsdata_val.to_torch_data_loader(roll=True, lookback=48, horizon=1)\n",
+    "val_data = tsdata_val.to_torch_data_loader(lookback=48, horizon=1)\n",
     "\n",
     "# uncomment this line to change `val_data` as numpy ndarray\n",
     "# val_data = tsdata_val.roll(lookback=48, horizon=1).to_numpy()"
diff --git a/docs/readthedocs/source/doc/Chronos/Overview/data_processing_feature_engineering.md b/docs/readthedocs/source/doc/Chronos/Overview/data_processing_feature_engineering.md
index 416c1a46e4b..ae7595003bf 100644
--- a/docs/readthedocs/source/doc/Chronos/Overview/data_processing_feature_engineering.md
+++ b/docs/readthedocs/source/doc/Chronos/Overview/data_processing_feature_engineering.md
@@ -189,9 +189,9 @@ Please refer to the API doc [`roll`](../../PythonAPI/Chronos/tsdataset.html#bigd
 .. note:: 
     **Difference between `roll` and `to_torch_data_loader`**:
     
-    `.roll(...)` performs the rolling before RR forecasters/auto models training while `.to_torch_data_loader(roll=True, ...)` performs rolling during the training.
+    `.roll(...)` performs the rolling before RR forecasters/auto models training while `.to_torch_data_loader(...)` performs rolling during the training.
     
-    It is fine to use either of them when you have a relatively small dataset (less than 1G). `.to_torch_data_loader(roll=True, ...)` is recommended when you have a large dataset (larger than 1G) to save memory usage.
+    It is fine to use either of them when you have a relatively small dataset (less than 1G). `.to_torch_data_loader(...)` is recommended when you have a large dataset (larger than 1G) to save memory usage.
 ```
 
 ```eval_rst