CODEWITHSUNDEEP
jupyter-notebookopenai-apilarge-language-modelgpt-3fine-tuning
Codezilla
Codezilla

Reputation: 21

AttributeError: 'OpenAI' object has no attribute 'fine_tunes'

I work with Python in Jupyter Notebook 7.0.8 :

Here is the error generated by the following cell:

The error:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[10], line 5
      2 dataset_path = r"*****"
      4 # Fine-tune the model with the examples from the dataset
----> 5 fine_tuned_model_id = fine_tune_model_with_examples(dataset_path)
      6 print(f"Fine-tuned model ID: {fine_tuned_model_id}")
      8 # Example source code to analyze

Cell In[9], line 34, in fine_tune_model_with_examples(dataset_path)
     26 # Launch fine-tuning
     27 fine_tuning_parameters = {
     28     "training_file": train_file_id,
     29     "validation_file": test_file_id,
     30     "model": "gpt-3.5-turbo",
     31     "n_epochs": 4
     32 }
---> 34 response = client.fine_tunes.create(**fine_tuning_parameters)
     35 return response['id']

AttributeError: 'OpenAI' object has no attribute 'fine_tunes'

The cell causing the error:

# Function to fine-tune the model
def fine_tune_model_with_examples(dataset_path):
    # Load and balance the dataset
    balanced_dataset = load_and_balance_dataset(dataset_path)

    # Split the dataset into training and test sets
    train_set, test_set = split_dataset(balanced_dataset)

    # Prepare fine-tuning data in chat format
    train_examples = prepare_fine_tuning_data(train_set)
    test_examples = prepare_fine_tuning_data(test_set)

    # Save training and test data to JSONL files
    save_to_jsonl(train_examples, "train_fine_tuning_data.jsonl")
    save_to_jsonl(test_examples, "test_fine_tuning_data.jsonl")

    # Upload training and test data to OpenAI
    with open("train_fine_tuning_data.jsonl", 'rb') as train_file:
        train_file_response = client.files.create(file=train_file, purpose='fine-tune')
    with open("test_fine_tuning_data.jsonl", 'rb') as test_file:
        test_file_response = client.files.create(file=test_file, purpose='fine-tune')

    train_file_id = train_file_response.id
    test_file_id = test_file_response.id

    # Launch fine-tuning
    fine_tuning_parameters = {
        "training_file": train_file_id,
        "validation_file": test_file_id,
        "model": "gpt-3.5-turbo",
        "n_epochs": 4
    }

    response = client.fine_tunes.create(**fine_tuning_parameters)
    return response['id']

I made sure to update all the packages used.

However, it is indicated (https://github.com/openai/openai-python/discussions/742) among the changes made with the update of the OpenAI API that: openai.FineTune.create() is now client.fine_tunes.create().

Does anyone have a solution to suggest to me?

Thank you in advance ;)

Upvotes: 1

Views: 315

Answers (1)

Codezilla
Codezilla

Reputation: 21

I was able to solve the issue by replacing the portion of code that was no longer compatible with API V1:

# Upload training and test data to OpenAI
with open("*****.jsonl", 'rb') as train_file:
    train_file_response = client.files.create(file=train_file, purpose='fine-tune')

Thank you for the help.

Upvotes: 0

Related Questions