"Fine-tuning improves the model by training on many more examples than can fit in a prompt, letting you achieve better results on a wide number of tasks. This notebook provides a step-by-step guide for our new GPT-4o mini fine-tuning. We'll perform entity extraction using the [RecipeNLG dataset](https://github.com/Glorf/recipenlg), which provides various recipes and a list of extracted generic ingredients for each. This is a common dataset for named entity recognition (NER) tasks.\n",
"\n",
"Note: **GPT-4o mini fine-tuning is available to developers in our [Tier 4 and 5 usage tiers](https://platform.openai.com/docs/guides/rate-limits/usage-tiers).** You can start fine-tuning GPT-4o mini by visiting your fine-tuning dashboard, clicking \"create\", and selecting “gpt-4o-mini-2024-07-18” from the base model drop-down.\n",
"1. **Setup:** Loading our dataset and filtering down to one domain to fine-tune on.\n",
"2. **Data preparation:** Preparing your data for fine-tuning by creating training and validation examples, and uploading them to the `Files` endpoint.\n",
"For more information on fine-tuning, you can refer to our [documentation guide](https://platform.openai.com/docs/guides/fine-tuning) or [API reference](https://platform.openai.com/docs/api-reference/fine-tuning).\n"
"Fine-tuning works best when focused on a particular domain. It's important to make sure your dataset is both focused enough for the model to learn, but general enough that unseen examples won't be missed. Having this in mind, we have extracted a subset from the RecipesNLG dataset to only contain documents from [cookbooks.com](https://cookbooks.com/).\n"
"We'll begin by preparing our data. When fine-tuning with the `ChatCompletion` format, each training example is a simple list of `messages`. For example, an entry could look like:\n",
"\n",
"```\n",
"[{'role': 'system',\n",
" 'content': 'You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.'},\n",
"\n",
" {'role': 'user',\n",
" 'content': 'Title: No-Bake Nut Cookies\\n\\nIngredients: [\"1 c. firmly packed brown sugar\", \"1/2 c. evaporated milk\", \"1/2 tsp. vanilla\", \"1/2 c. broken nuts (pecans)\", \"2 Tbsp. butter or margarine\", \"3 1/2 c. bite size shredded rice biscuits\"]\\n\\nGeneric ingredients: '},\n",
"During the training process this conversation will be split, with the final entry being the `completion` that the model will produce, and the remainder of the `messages` acting as the prompt. Consider this when building your training examples - if your model will act on multi-turn conversations, then please provide representative examples so it doesn't perform poorly when the conversation starts to expand.\n",
"\n",
"Please note that currently there is a 4096 token limit for each training example. Anything longer than this will be truncated at 4096 tokens.\n"
"Let's now do this for a subset of the dataset to use as our training data. You can begin with even 30-50 well-pruned examples. You should see performance continue to scale linearly as you increase the size of the training set, but your jobs will also take longer.\n"
"{'messages': [{'role': 'system', 'content': 'You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.'}, {'role': 'user', 'content': 'Title: No-Bake Nut Cookies\\n\\nIngredients: [\"1 c. firmly packed brown sugar\", \"1/2 c. evaporated milk\", \"1/2 tsp. vanilla\", \"1/2 c. broken nuts (pecans)\", \"2 Tbsp. butter or margarine\", \"3 1/2 c. bite size shredded rice biscuits\"]\\n\\nGeneric ingredients: '}, {'role': 'assistant', 'content': '[\"brown sugar\", \"milk\", \"vanilla\", \"nuts\", \"butter\", \"bite size shredded rice biscuits\"]'}]}\n",
"{'messages': [{'role': 'system', 'content': 'You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.'}, {'role': 'user', 'content': 'Title: Jewell Ball\\'S Chicken\\n\\nIngredients: [\"1 small jar chipped beef, cut up\", \"4 boned chicken breasts\", \"1 can cream of mushroom soup\", \"1 carton sour cream\"]\\n\\nGeneric ingredients: '}, {'role': 'assistant', 'content': '[\"beef\", \"chicken breasts\", \"cream of mushroom soup\", \"sour cream\"]'}]}\n",
"{'messages': [{'role': 'system', 'content': 'You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.'}, {'role': 'user', 'content': 'Title: Creamy Corn\\n\\nIngredients: [\"2 (16 oz.) pkg. frozen corn\", \"1 (8 oz.) pkg. cream cheese, cubed\", \"1/3 c. butter, cubed\", \"1/2 tsp. garlic powder\", \"1/2 tsp. salt\", \"1/4 tsp. pepper\"]\\n\\nGeneric ingredients: '}, {'role': 'assistant', 'content': '[\"frozen corn\", \"cream cheese\", \"butter\", \"garlic powder\", \"salt\", \"pepper\"]'}]}\n",
"{'messages': [{'role': 'system', 'content': 'You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.'}, {'role': 'user', 'content': 'Title: Chicken Funny\\n\\nIngredients: [\"1 large whole chicken\", \"2 (10 1/2 oz.) cans chicken gravy\", \"1 (10 1/2 oz.) can cream of mushroom soup\", \"1 (6 oz.) box Stove Top stuffing\", \"4 oz. shredded cheese\"]\\n\\nGeneric ingredients: '}, {'role': 'assistant', 'content': '[\"chicken\", \"chicken gravy\", \"cream of mushroom soup\", \"shredded cheese\"]'}]}\n",
"{'messages': [{'role': 'system', 'content': 'You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.'}, {'role': 'user', 'content': 'Title: Reeses Cups(Candy) \\n\\nIngredients: [\"1 c. peanut butter\", \"3/4 c. graham cracker crumbs\", \"1 c. melted butter\", \"1 lb. (3 1/2 c.) powdered sugar\", \"1 large pkg. chocolate chips\"]\\n\\nGeneric ingredients: '}, {'role': 'assistant', 'content': '[\"peanut butter\", \"graham cracker crumbs\", \"butter\", \"powdered sugar\", \"chocolate chips\"]'}]}\n"
]
}
],
"source": [
"# use the first 100 rows of the dataset for training\n",
"In addition to training data, we can also **optionally** provide validation data, which will be used to make sure that the model does not overfit your training set.\n"
"{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.\"}, {\"role\": \"user\", \"content\": \"Title: No-Bake Nut Cookies\\n\\nIngredients: [\\\"1 c. firmly packed brown sugar\\\", \\\"1/2 c. evaporated milk\\\", \\\"1/2 tsp. vanilla\\\", \\\"1/2 c. broken nuts (pecans)\\\", \\\"2 Tbsp. butter or margarine\\\", \\\"3 1/2 c. bite size shredded rice biscuits\\\"]\\n\\nGeneric ingredients: \"}, {\"role\": \"assistant\", \"content\": \"[\\\"brown sugar\\\", \\\"milk\\\", \\\"vanilla\\\", \\\"nuts\\\", \\\"butter\\\", \\\"bite size shredded rice biscuits\\\"]\"}]}\n",
"{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.\"}, {\"role\": \"user\", \"content\": \"Title: Jewell Ball'S Chicken\\n\\nIngredients: [\\\"1 small jar chipped beef, cut up\\\", \\\"4 boned chicken breasts\\\", \\\"1 can cream of mushroom soup\\\", \\\"1 carton sour cream\\\"]\\n\\nGeneric ingredients: \"}, {\"role\": \"assistant\", \"content\": \"[\\\"beef\\\", \\\"chicken breasts\\\", \\\"cream of mushroom soup\\\", \\\"sour cream\\\"]\"}]}\n",
"{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.\"}, {\"role\": \"user\", \"content\": \"Title: Creamy Corn\\n\\nIngredients: [\\\"2 (16 oz.) pkg. frozen corn\\\", \\\"1 (8 oz.) pkg. cream cheese, cubed\\\", \\\"1/3 c. butter, cubed\\\", \\\"1/2 tsp. garlic powder\\\", \\\"1/2 tsp. salt\\\", \\\"1/4 tsp. pepper\\\"]\\n\\nGeneric ingredients: \"}, {\"role\": \"assistant\", \"content\": \"[\\\"frozen corn\\\", \\\"cream cheese\\\", \\\"butter\\\", \\\"garlic powder\\\", \\\"salt\\\", \\\"pepper\\\"]\"}]}\n",
"{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.\"}, {\"role\": \"user\", \"content\": \"Title: Chicken Funny\\n\\nIngredients: [\\\"1 large whole chicken\\\", \\\"2 (10 1/2 oz.) cans chicken gravy\\\", \\\"1 (10 1/2 oz.) can cream of mushroom soup\\\", \\\"1 (6 oz.) box Stove Top stuffing\\\", \\\"4 oz. shredded cheese\\\"]\\n\\nGeneric ingredients: \"}, {\"role\": \"assistant\", \"content\": \"[\\\"chicken\\\", \\\"chicken gravy\\\", \\\"cream of mushroom soup\\\", \\\"shredded cheese\\\"]\"}]}\n",
"{\"messages\": [{\"role\": \"system\", \"content\": \"You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided.\"}, {\"role\": \"user\", \"content\": \"Title: Reeses Cups(Candy) \\n\\nIngredients: [\\\"1 c. peanut butter\\\", \\\"3/4 c. graham cracker crumbs\\\", \\\"1 c. melted butter\\\", \\\"1 lb. (3 1/2 c.) powdered sugar\\\", \\\"1 large pkg. chocolate chips\\\"]\\n\\nGeneric ingredients: \"}, {\"role\": \"assistant\", \"content\": \"[\\\"peanut butter\\\", \\\"graham cracker crumbs\\\", \\\"butter\\\", \\\"powdered sugar\\\", \\\"chocolate chips\\\"]\"}]}\n"
]
}
],
"source": [
"# print the first 5 lines of the training file\n",
"Now we can create our fine-tuning job with the generated files and an optional suffix to identify the model. The response will contain an `id` which you can use to retrieve updates on the job.\n",
"Note: The files have to first be processed by our system, so you might get a `File not ready` error. In that case, simply retry a few minutes later.\n"
"You can make a `GET` request to the `https://api.openai.com/v1/alpha/fine-tunes` endpoint to list your alpha fine-tune jobs. In this instance you'll want to check that the ID you got from the previous step ends up as `status: succeeded`.\n",
"\n",
"Once it is completed, you can use the `result_files` to sample the results from the validation set (if you uploaded one), and use the ID from the `fine_tuned_model` parameter to invoke your trained model.\n"
"The last step is to use your fine-tuned model for inference. Similar to the classic `FineTuning`, you simply call `ChatCompletions` with your new fine-tuned model name filling the `model` parameter.\n"
