Skip to main content
Supervised Fine-Tuning (SFT) trains a language model on labeled conversation data so it learns to follow instructions, adopt a persona, or respond in a specific style.

​
Prerequisites

  • An EigenAI account with available credits.
  • A training dataset in JSONL format.

​
Create an SFT job

Click Fine-Tune a Model on the Fine-tuning page, then select the SFT tab to open the 6-step wizard.

​
Step 1 — Model

Select a Base model.
ModelPrice
Qwen3-4B-Instruct-2507$0.4 / M tokens
Qwen3-30B-A3B-Instruct-2507$2.8 / M tokens
Qwen3-30B-A3B-Thinking-2507$2.8 / M tokens
Qwen3-235B-A22B-Instruct-2507$20 / M tokens

​
Step 2 — Dataset

Upload your training data or select a previously uploaded dataset.
FieldDescription
Dataset formatThe format of your training file. Currently supports Conversation (chat JSONL).
Select existing datasetReuse a dataset you have already uploaded.
File uploadDrag and drop a .jsonl file or click to browse.
Your training file must be a JSONL file where each line is a JSON object containing a messages array in OpenAI chat format: 
{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"}, {"role": "assistant", "content": "Hi there!"}]}

​
Step 3 — Evaluation

Choose how to validate the model during training.
OptionDescription
Do not use a validation datasetSkip evaluation for the fastest training run.
Automatically split a portion of the training datasetReserve part of your training data for evaluation. (Coming soon)
Use a custom dataset for evaluationProvide a separate validation file. (Coming soon)

​
Step 4 — Params

Configure the training hyperparameters.
ParameterAuto defaultDescription
Number of epochs5How many times the model trains over the full dataset.
Learning rate multiplier1.0× (effective rate: 2.00e-5)Scales the base learning rate.
Model output nameft-<timestamp>-<random-string>The name shown for the resulting fine-tuned model.
Each parameter has an Auto mode that applies sensible defaults and a Custom mode for manual entry.

​
Step 5 — WandB

Optionally connect Weights & Biases to track your experiment.
FieldDescription
WandB API keyYour WandB API key. Leave blank to skip tracking.

​
Step 6 — Review

Review the estimated cost before starting training.
FieldDescription
ModelThe selected base model.
TokensEstimated number of tokens in your dataset.
EpochsNumber of training epochs.
Estimated costTotal credit cost for this training run.
Check the acknowledgment box and click Confirm & Create to submit the job.