Update Gemini version: llm_tuning

Author: takumiohym

notebooks/vertex_genai/labs/vertex_llm_tuning_with_gemini.ipynb

@@ -202,7 +202,7 @@
     "}\n",
     "```\n",
     "\n",
-    "This is the format example we need to tune a Gemini 1.5 model.\n",
+    "This is the format example we need to tune a Gemini 2.0 Flash model.\n",
     "\n",
     "Please refer to [the document](https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini-supervised-tuning-prepare#dataset_example_for_gemini-15-pro_and_gemini-15-flash) to check other fields you can use.\n",
     "\n",
@@ -393,7 +393,7 @@
    "source": [
     "client = genai.Client(vertexai=True, location=\"us-central1\")\n",
     "\n",
-    "base_model = \"gemini-1.5-pro-002\"\n",
+    "base_model = \"gemini-2.0-flash-001\"\n",
     "\n",
     "training_dataset = types.TuningDataset(\n",
     "    gcs_uri=TRAINING_DATA_URI,\n",
@@ -634,7 +634,7 @@
     "\n",
     "#### Model tuning metrics\n",
     "\n",
-    "The model tuning job automatically collects the following tuning metrics for `gemini-1.5-pro-002`.\n",
+    "The model tuning job automatically collects the following tuning metrics for `gemini-2.0-flash`.\n",
     "\n",
     "* `/train_total_loss`: Loss for the tuning dataset at a training step.\n",
     "* `/train_fraction_of_correct_next_step_preds`: The token accuracy at a training step. A single prediction consists of a sequence of tokens. This metric measures the accuracy of the predicted tokens when compared to the ground truth in the tuning dataset.\n",

notebooks/vertex_genai/solutions/vertex_llm_tuning_with_gemini.ipynb

@@ -202,7 +202,7 @@
     "}\n",
     "```\n",
     "\n",
-    "This is the format example we need to tune a Gemini 1.5 model.\n",
+    "This is the format example we need to tune a Gemini 2.0 Flash model.\n",
     "\n",
     "Please refer to [the document](https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini-supervised-tuning-prepare#dataset_example_for_gemini-15-pro_and_gemini-15-flash) to check other fields you can use.\n",
     "\n",
@@ -404,7 +404,7 @@
    "source": [
     "client = genai.Client(vertexai=True, location=\"us-central1\")\n",
     "\n",
-    "base_model = \"gemini-1.5-pro-002\"\n",
+    "base_model = \"gemini-2.0-flash-001\"\n",
     "\n",
     "training_dataset = types.TuningDataset(\n",
     "    gcs_uri=TRAINING_DATA_URI,\n",
@@ -647,7 +647,7 @@
     "\n",
     "#### Model tuning metrics\n",
     "\n",
-    "The model tuning job automatically collects the following tuning metrics for `gemini-1.5-pro-002`.\n",
+    "The model tuning job automatically collects the following tuning metrics for `gemini-2.0-flash`.\n",
     "\n",
     "* `/train_total_loss`: Loss for the tuning dataset at a training step.\n",
     "* `/train_fraction_of_correct_next_step_preds`: The token accuracy at a training step. A single prediction consists of a sequence of tokens. This metric measures the accuracy of the predicted tokens when compared to the ground truth in the tuning dataset.\n",