update phrasing

examples/fine-tune-smollm2-on-synthetic-data.ipynb

@@ -75,18 +75,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/davidberenstein/Documents/programming/argilla/synthetic-data-generator/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Import necessary libraries\n",
     "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
@@ -229,7 +220,16 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "For the example, we did not use a specific validation set but we can see the loss is decreasing, so we assume the model is generalsing well to the training data. To get a better understanding of the model's performance, let's test it again with the same prompt. \n",
+    "```\n",
+    "# {'loss': 1.4498, 'grad_norm': 2.3919131755828857, 'learning_rate': 4e-05, 'epoch': 0.1}\n",
+    "# {'loss': 1.362, 'grad_norm': 1.6650595664978027, 'learning_rate': 3e-05, 'epoch': 0.19}\n",
+    "# {'loss': 1.3778, 'grad_norm': 1.4778285026550293, 'learning_rate': 2e-05, 'epoch': 0.29}\n",
+    "# {'loss': 1.3735, 'grad_norm': 2.1424977779388428, 'learning_rate': 1e-05, 'epoch': 0.39}\n",
+    "# {'loss': 1.3512, 'grad_norm': 2.3498542308807373, 'learning_rate': 0.0, 'epoch': 0.48}\n",
+    "# {'train_runtime': 1911.514, 'train_samples_per_second': 1.046, 'train_steps_per_second': 0.262, 'train_loss': 1.3828572998046875, 'epoch': 0.48}\n",
+    "```\n",
+    "\n",
+    "For the example, we did not use a specific validation set but we can see the loss is decreasing, so we assume the model is generalsing well to the training data. To get a better understanding of the model's performance, let's test it again with the same prompt.\n",
     "\n",
     "### Run inference\n",
     "\n",
@@ -238,12 +238,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Device set to use mps\n"
+     ]
+    }
+   ],
    "source": [
-    "pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer)\n",
-    "pipe(prompt, max_new_tokens=100)"
+    "from transformers import pipeline\n",
+    "prompt = \"What is the primary function of mitochondria within a cell?\"\n",
+    "generator = pipeline(\n",
+    "    \"text-generation\",\n",
+    "    model=\"argilla/SmolLM2-360M-synthetic-concise-reasoning\",\n",
+    "    device=\"mps\",\n",
+    ")\n",
+    "generator(\n",
+    "    [{\"role\": \"user\", \"content\": prompt}], max_new_tokens=128, return_full_text=False\n",
+    ")[0][\"generated_text\"]"
    ]
   },
   {