Fine Tune Not Going Through

API
1

Hello! I’m trying to finetune a model with the following code:
from openai import OpenAI
client = OpenAI()

client.fine_tuning.jobs.create(
training_file=“file-CiesR2UYJ3SQXvBxhhB47kgq”,
validation_file=“file-Ajbx1GMt32Blqn1hn3DrVNfm”,

model=“davinci-002”,
hyperparameters={
“n_epochs”:2
}
)

It doesn’t seem to be going through, with the following output:
FineTuningJob(id=[REDACTED], created_at=1715984133, error=Error(code=None, message=None, param=None), fine_tuned_model=None, finished_at=None, hyperparameters=Hyperparameters(n_epochs=2, batch_size=‘auto’, learning_rate_multiplier=‘auto’), model=‘davinci-002’, object=‘fine_tuning.job’, organization_id=‘[REDACTED]’, result_files=, seed=546001256, status=‘validating_files’, trained_tokens=None, training_file=‘[REDACTED]’, validation_file=‘[REDACTED]’, estimated_finish=None, integrations=, user_provided_suffix=None)

Any ideas why? Thank you for the help!

2

You have to wait sometimes hours for the uploaded JSONL files to be ready before they are available for the “create fine-tuning” API call.

After you upload the file, it may take some time to process. While the file is processing, you can still create a fine-tuning job but it will not start until the file processing has completed.

The file object can return “status” and “status-details” when you use the storage API option to list files, but this return is deprecated since they now made fine-tuning wait instead of fail.