So, I am trying to fine tune a model on the OpenAI plataform. My dataset is good in terms of formatation, but Im getting “Error creating job: Invalid field ‘method’, extra fields are not allowed” on the plataform. I don’t get it, can someone help me, please?
I was able to get around it by triggering the job with a python script
import openai
from openai import OpenAI
openai.api_key = "your-api-key"
client = OpenAI(api_key=openai.api_key)
# Define the training file ID and the model to fine-tune
training_file_id = "file-your-file"
model_to_fine_tune = "gpt-4o-mini-2024-07-18" # Replace with your desired model
try:
# Create a fine-tuning job
fine_tune_job = client.fine_tuning.jobs.create(
model=model_to_fine_tune,
training_file=training_file_id,
)
print("Fine-tuning job created successfully!")
except openai.error.APIConnectionError as e:
print("The server could not be reached.")
print(e)
except openai.error.RateLimitError as e:
print("Rate limit exceeded; please wait and try again.")
print(e)
except openai.error.APIError as e:
print(f"An API error occurred: {e}")
I now have a job that is “Waiting”. This is my first time doing fine tuning, so I do not know if waiting for a few minutes is expected or is related issue to the current problem with what seems to be with the web frontend.