|
63 | 63 | "# Register dataset in SageMaker AI Registry\n", |
64 | 64 | "# This creates a versioned dataset that can be referenced by ARN\n", |
65 | 65 | "'''dataset = DataSet.create(\n", |
66 | | - " name=\"demo-nargokul-6\", \n", |
| 66 | + " name=\"demo-6\",\n", |
67 | 67 | " data_location=\"s3://nova-mlflow-us-west-2/dataset/preference_dataset_train_256.jsonl\", \n", |
68 | 68 | " customization_technique=CustomizationTechnique.DPO, \n", |
69 | 69 | " wait=True\n", |
|
116 | 116 | { |
117 | 117 | "cell_type": "code", |
118 | 118 | "id": "0352bdaa-fa13-44c5-a70c-0d9bf7a10477", |
119 | | - "metadata": {}, |
| 119 | + "metadata": { |
| 120 | + "ExecuteTime": { |
| 121 | + "end_time": "2025-12-05T19:30:51.233369Z", |
| 122 | + "start_time": "2025-12-05T19:30:51.101703Z" |
| 123 | + } |
| 124 | + }, |
120 | 125 | "source": [ |
121 | 126 | "# Create DPOTrainer instance with comprehensive configuration\n", |
122 | 127 | "trainer = DPOTrainer(\n", |
|
159 | 164 | "\n", |
160 | 165 | "print(f\"Training completed! Job ARN: {training_job.training_job_arn}\")" |
161 | 166 | ], |
162 | | - "outputs": [], |
163 | | - "execution_count": null |
| 167 | + "outputs": [ |
| 168 | + { |
| 169 | + "ename": "NameError", |
| 170 | + "evalue": "name 'DataSet' is not defined", |
| 171 | + "output_type": "error", |
| 172 | + "traceback": [ |
| 173 | + "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m", |
| 174 | + "\u001B[0;31mNameError\u001B[0m Traceback (most recent call last)", |
| 175 | + "Cell \u001B[0;32mIn[1], line 2\u001B[0m\n\u001B[1;32m 1\u001B[0m \u001B[38;5;66;03m# Create DPOTrainer instance with comprehensive configuration\u001B[39;00m\n\u001B[0;32m----> 2\u001B[0m dataset \u001B[38;5;241m=\u001B[39m \u001B[43mDataSet\u001B[49m\u001B[38;5;241m.\u001B[39mget(name\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124marn:aws:sagemaker:us-east-1:729646638167:hub-content/sdktest/DataSet/dpo-nova-1-test-data/0.0.1\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[1;32m 4\u001B[0m trainer \u001B[38;5;241m=\u001B[39m DPOTrainer(\n\u001B[1;32m 5\u001B[0m \u001B[38;5;66;03m# Base model from SageMaker Hub\u001B[39;00m\n\u001B[1;32m 6\u001B[0m model\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mmeta-textgeneration-llama-3-2-1b-instruct\u001B[39m\u001B[38;5;124m\"\u001B[39m,\n\u001B[0;32m (...)\u001B[0m\n\u001B[1;32m 28\u001B[0m accept_eula\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mTrue\u001B[39;00m\n\u001B[1;32m 29\u001B[0m )\n\u001B[1;32m 31\u001B[0m \u001B[38;5;66;03m# Customize training hyperparameters\u001B[39;00m\n\u001B[1;32m 32\u001B[0m \u001B[38;5;66;03m# DPO-specific parameters are automatically loaded from the model's recipe\u001B[39;00m\n", |
| 176 | + "\u001B[0;31mNameError\u001B[0m: name 'DataSet' is not defined" |
| 177 | + ] |
| 178 | + } |
| 179 | + ], |
| 180 | + "execution_count": 1 |
164 | 181 | }, |
165 | 182 | { |
166 | 183 | "cell_type": "code", |
|
0 commit comments