/fine_tuning/jobsCreate a fine-tuning job
Creates a fine-tuning job that begins training a new model from an uploaded dataset. Supply model and training_file, and optionally configure validation, fine-tuning methods, hyperparameters, integrations, a suffix, seed, and metadata. The response contains the enqueued job and its current status; poll the fine-tuning job resource for progress.
- RetriesRetries up to 2×, 500ms backoff, 30s timeout.
Fine-tuning job configuration containing the base model, training dataset, and optional validation and optimization settings.
model and training_file are required. training_file must identify an uploaded JSONL file whose purpose is fine-tune; method.type must be supervised, dpo, or reinforcement, and a reinforcement method must include grader. seed must be between 0 and 2147483647, while suffix must contain 1 to 64 characters.