FAQs for Troubleshooting A Fine-Tuned Model
FAQs for Troubleshooting A Fine-Tuned Model
docsFAQs for Troubleshooting A Fine-Tuned Model
Cohere’s fine-tuning feature was deprecated on September 15, 2025
Trainings are completed sequentially, and when you launch a training session, it is added to the end of a queue. Depending on the length of our training queue, training may take between an hour and a day to complete.
To use your trained model in our API or SDKs, you must call it by its model UUID and not by its name. To get the model UUID, select the model in the playground and click Export Code. Select the language you are using and copy the code to call the model.
This is a screenshot of how to locate the model path to call your custom model.
Our engineers review every individual failed training run and will attempt to rectify it, without any action on your part. We reach out to individuals with failed custom models we cannot resolve manually.
We recommend generating samples from both the base model and the fine-tuned model on a test set. Then, compare these examples directly through human evaluations.
Standard organizations are allowed 10 jobs per day (15 jobs in total), while enterprises are allowed 25 jobs per day (with no limit on total).
No, we do not delete any fine-tuned models.
Please reach out to support@cohere.com or post in our Discord if you have unanswered questions about fine-tuning.