Hi all! I hope you’re well.
My problem is:
I already succeeded to fine-tune ChatGPT-3.5, but I’m blocking on a new attempt with another file.
I have this error message:
InvalidRequestError: An error occurred while processing file ‘file-nameofthefile’ and it cannot be used for fine-tuning. Details may be available in the file’s status_details.
But how to access to this status_details to have more information about the problem in the file?
These are the supplementary methods for fine-tune jobs and the new endpoint (ensure python openai library is updated to latest):
# List 10 fine-tuning jobs
openai.FineTuningJob.list(limit=10)
# Retrieve the state of a fine-tune
openai.FineTuningJob.retrieve("ft-abc123")
# Cancel a job
openai.FineTuningJob.cancel("ft-abc123")
# List up to 10 events from a fine-tuning job
openai.FineTuningJob.list_events(id="ft-abc123", limit=10)
# Delete a fine-tuned model (must be an owner of the org the model was created in)
openai.Model.delete("ft-abc123")
Since the problem is in the fine tuning file, ensure that it is a valid list of JSONs. It should be separable by carriage return into individual conversation examples that can be processed by json.loads or as python list/dictionary objects without errors.
Thank you, I 've succeeded to submit it dividing the jsonl in multiple parts. This way, instead of having just “errors” I was able to obtain more precise information.