Skip to main content
Once you have your prerequisites ready, launching a training run takes a few minutes.

​
Start a new job

Go to the Training tab in the dashboard and click New Training Job.
New Training Job form in the dashboard
1

Select a training dataset

Choose the dataset the model will learn from. You can build a dataset from live traffic, upload a JSONL file, or use task tags to filter captured traffic for clean, focused samples.
2

Select an eval dataset

Choose the dataset used for evaluations throughout training. Must have zero overlap with training data.
3

Select a rubric

Choose the rubric that defines your quality criteria. Make sure you’ve validated it against your eval dataset first.
4

Select a recipe

Choose a recipe based on task difficulty and capability needs.
5

Start training

Review your selections and click Start Training to queue the job.

​
Training job lifecycle

Once started, your job moves through these statuses:
StatusWhat’s happening
Exporting datasetsYour training and eval data is being prepared
QueuedJob is waiting for available compute
StartingGPUs are being allocated and the training environment is initializing
RunningThe model is actively training
CompletedTraining finished successfully
If something goes wrong, the job will show one of these:
StatusWhat it means
FailedSomething went wrong — check the logs on the training details page
CancelledThe run was cancelled
Timed outThe run exceeded the maximum allowed duration
Training can take anywhere from around 10 minutes to 10+ hours depending on dataset size and recipe. Once running, monitor progress from the training details page.