Update 14_spot_ray_hpt_torch_cifar10.ipynb

criterion -> loss_function

Author: bartzbeielstein

notebooks/14_spot_ray_hpt_torch_cifar10.ipynb

@@ -857,6 +857,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {},
       "source": [
@@ -905,7 +906,12 @@
         "\n",
         "### Loss Functions and Metrics\n",
         "\n",
-        "The key `\"criterion\"` specifies the loss function which is used during the optimization. There are several different loss functions under `PyTorch`'s nn package. For example, a simple loss is `MSELoss`, which computes the mean-squared error between the output and the target. In this tutorial we will use `CrossEntropyLoss`, because it is also used in the `PyTorch` tutorial."
+        "::: {.callout-warning}\n",
+        "#### Use of the Key `\"criterion\"` is deprecated as of `v.0.1.5`\n",
+        "Starting with version `v.0.1.5` `spotPython` uses the key `\"loss_function\"` for loss functions instead of `\"criterion\"`.\n",
+        ":::\n",
+        "\n",
+        "The key `\"loss_function\"` specifies the loss function which is used during the optimization. There are several different loss functions under `PyTorch`'s nn package. For example, a simple loss is `MSELoss`, which computes the mean-squared error between the output and the target. In this tutorial we will use `CrossEntropyLoss`, because it is also used in the `PyTorch` tutorial."
       ]
     },
     {
@@ -914,7 +920,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "fun_control = modify_hyper_parameter_levels(fun_control, \"criterion\", [\"CrossEntropyLoss\"])"
+        "fun_control = modify_hyper_parameter_levels(fun_control, \"loss_function\", [\"CrossEntropyLoss\"])"
       ]
     },
     {
@@ -933,7 +939,7 @@
       "source": [
         "#| echo: true\n",
         "weights = 1.0\n",
-        "criterion = CrossEntropyLoss\n",
+        "loss_function = CrossEntropyLoss\n",
         "shuffle = True\n",
         "eval = \"train_hold_out\"\n",
         "device = DEVICE\n",
@@ -952,7 +958,7 @@
         "               \"weight_coeff\": None,\n",
         "               \"metric\": None,\n",
         "               \"metric_sklearn\": None,\n",
-        "               \"criterion\": criterion,\n",
+        "               \"loss_function\": loss_function,\n",
         "               \"shuffle\": shuffle,\n",
         "               \"eval\": eval,\n",
         "               \"device\": device,\n",
@@ -2265,6 +2271,7 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
       "metadata": {},
       "source": [
@@ -2273,7 +2280,7 @@
         "```{raw}\n",
         "config: {'l1': 64, 'l2': 32, 'lr': 0.008391430243550081, \n",
         "    'batch_size': 4, 'epochs': 16, 'k_folds': 0, 'patience': 3,\n",
-        "    'optimizer': 'Adam', 'criterion': CrossEntropyLoss()}\n",
+        "    'optimizer': 'Adam', 'loss_function': CrossEntropyLoss()}\n",
         "Epoch: 9\n",
         "Batch:  1000. Batch Size: 4. Training Loss (running): 2.308\n",
         "Batch:  2000. Batch Size: 4. Training Loss (running): 1.153\n",