Training jobs API — start, poll, stop, and download

Training jobs are the core of Pioneer’s fine-tuning platform. You submit a job with a base model and one or more datasets, and Pioneer handles the rest — provisioning compute, training the model, and making checkpoints available for download or deployment. Both LoRA and full fine-tuning are supported for encoder and decoder architectures.

base_model is required when starting a training job. Omitting it returns a 422 Unprocessable Entity error. Supply a model ID from GET /base-models (e.g. fastino/gliner2-base-v1, Qwen/Qwen3-8B) or a checkpoint UUID from a previous training job.

Job status lifecycle

Status	Description
`requested`	Job has been submitted and is queued for provisioning.
`running`	Training is actively in progress.
`complete`	Training finished successfully. Metrics and checkpoints are available.
`failed`	Training encountered an error. Check logs for details.
`deployed`	Model has been deployed and is serving inference traffic.
`cancelled`	Job was manually stopped via `POST /felix/training-jobs/:id/stop`.

Start a training job

POST /felix/training-jobs Submits a new fine-tuning job. Returns immediately with a job ID and requested status — use GET /felix/training-jobs/:id to poll for progress.

Rate limit for this endpoint is 20 requests per minute per user.

Request body

string

required

The model to fine-tune. Use a supported model ID returned by GET /base-models (e.g. fastino/gliner2-base-v1) or a checkpoint UUID from a previous training job.

object[]

required

Array of dataset references to train on. Each object must include a name field matching an existing dataset in the ready state.

string

required

A human-readable name for the resulting trained model. Defaults to a generated identifier if not provided.

string

Fine-tuning method to use. Accepted values: lora, full. Defaults to lora. Decoder LLM training is LoRA-only; full is reserved for GLiNER encoder models.

string

Post-training algorithm. Accepted values: sft (default), grpo, dpo. sft is supervised fine-tuning; grpo and dpo are reinforcement-learning methods that require rl_config. See the LLM fine-tuning guide for algorithm selection, dataset formats, and the supported-model matrix. Submitting grpo/dpo for a model that hasn’t been verified for RL returns a 422.

object

Reinforcement-learning hyperparameters. Required when training_algorithm is grpo or dpo; must be omitted for sft. Every key inside is optional (TRL-aligned server defaults are applied) except reward_type, which is required for GRPO.

Show rl_config keys

string

GRPO, required. Built-in reward function: exact_match, contains_substring, numeric_match, choice_match, regex_match, json_match, json_loose_match, rougeL_match, or llm_as_judge.

number

GRPO, DPO. Total optimizer steps.

number

GRPO. Completions sampled per prompt.

number

GRPO. KL penalty coefficient.

number

GRPO. Sampling temperature for rollouts.

number

GRPO. Max generated tokens per completion.

number

DPO. Preference sharpness (β).

string

DPO. DPO loss variant.

number

GRPO, DPO. Defaults to 25; lower for short smoke runs.

number

Number of training epochs. Defaults vary by base model.

number

Learning rate for the optimizer. For example, 5e-5.

curl -X POST https://api.pioneer.ai/felix/training-jobs \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "my-ner-model",
    "base_model": "fastino/gliner2-base-v1",
    "datasets": [{"name": "my-dataset"}],
    "training_type": "lora",
    "nr_epochs": 5,
    "learning_rate": 5e-5
  }'

curl -X POST https://api.pioneer.ai/felix/training-jobs \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "my-sft-model",
    "base_model": "Qwen/Qwen3-8B",
    "datasets": [{"name": "my-dataset"}],
    "training_type": "lora"
  }'

curl -X POST https://api.pioneer.ai/felix/training-jobs \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "my-grpo-model",
    "base_model": "Qwen/Qwen3-4B-Instruct-2507",
    "datasets": [{"name": "gsm8k-grpo"}],
    "training_type": "lora",
    "training_algorithm": "grpo",
    "rl_config": {"reward_type": "numeric_match", "max_steps": 100, "group_size": 8}
  }'

curl -X POST https://api.pioneer.ai/felix/training-jobs \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "my-dpo-model",
    "base_model": "meta-llama/Llama-3.1-8B-Instruct",
    "datasets": [{"name": "my-preferences"}],
    "training_type": "lora",
    "training_algorithm": "dpo",
    "rl_config": {"dpo_beta": 0.1}
  }'

Response

string

UUID of the training job. Use this ID in all subsequent requests.

string

Initial status, always requested on creation.

List training jobs

GET /felix/training-jobs Returns all training jobs for your account. Supports filtering to narrow results. Query parameters

string

Filter by job status. Accepted values: requested, running, complete, deployed, failed, cancelled.

string

Filter by project ID to show only jobs associated with a specific project.

curl "https://api.pioneer.ai/felix/training-jobs?status=complete" \
  -H "X-API-Key: YOUR_API_KEY"

number

Maximum number of jobs to return. Accepts 1–200. Defaults to 200.

number

Number of jobs to skip for pagination. Defaults to 0

Get training job status

GET /felix/training-jobs/:id Returns current status, configuration, and metrics for a specific training job. Path parameters

string

required

The training job UUID.

curl https://api.pioneer.ai/felix/training-jobs/YOUR_TRAINING_JOB_ID \
  -H "X-API-Key: YOUR_API_KEY"

Response

string

Training job UUID.

string

Current job status.

object

Performance metrics. Only present when status is complete.

Show metrics properties

number

F1 score on the evaluation split. Example: 0.94.

number

Precision score. Example: 0.96.

number

Recall score. Example: 0.92.

Get training logs

GET /felix/training-jobs/:id/logs Streams or returns the training logs for a job. Useful for debugging failed jobs or monitoring training progress in real time. Path parameters

string

required

The training job UUID.

curl https://api.pioneer.ai/felix/training-jobs/YOUR_TRAINING_JOB_ID/logs \
  -H "X-API-Key: YOUR_API_KEY"

List checkpoints

GET /felix/training-jobs/:id/checkpoints Returns all saved checkpoints for a training job. Checkpoint UUIDs can be used as the base_model value in a new training job to continue training from an intermediate state. Path parameters

string

required

The training job UUID.

curl https://api.pioneer.ai/felix/training-jobs/YOUR_TRAINING_JOB_ID/checkpoints \
  -H "X-API-Key: YOUR_API_KEY"

Download model weights

GET /felix/training-jobs/:id/download Returns a download URL for the trained model weights. Only available once the job status is complete. Path parameters

string

required

The training job UUID.

curl https://api.pioneer.ai/felix/training-jobs/YOUR_TRAINING_JOB_ID/download \
  -H "X-API-Key: YOUR_API_KEY"

Stop a running job

POST /felix/training-jobs/:id/stop Gracefully stops a job that is currently in running state. The job transitions to cancelled status… Path parameters

string

required

The training job UUID.

curl -X POST https://api.pioneer.ai/felix/training-jobs/YOUR_TRAINING_JOB_ID/stop \
  -H "X-API-Key: YOUR_API_KEY"

Delete a training job

DELETE /felix/training-jobs/:id Permanently deletes a training job and its associated artifacts, including checkpoints and logs.

Deleting a training job also removes the model weights. Make sure you have downloaded or deployed the model before deleting the job if you want to retain access to it.

Path parameters

string

required

The training job UUID.

curl -X DELETE https://api.pioneer.ai/felix/training-jobs/YOUR_TRAINING_JOB_ID \
  -H "X-API-Key: YOUR_API_KEY"

Returns 200 with {"success": true, "message": "..."} on success.

List all trained models

GET /felix/trained-models Returns a flat list of all successfully trained models across all of your training jobs.

curl https://api.pioneer.ai/felix/trained-models \
  -H "X-API-Key: YOUR_API_KEY"

Data Privacy: If you would like to opt out of having your data used in Fastino’s model training, please email support@fastino.ai and we will ensure your data is excluded from our training pipelines.

Get Started

Integrations

Core Concepts

API Reference

Guides

Account

Training jobs API — start, poll, stop, and download

Job status lifecycle

Start a training job

List training jobs

Get training job status

Get training logs

List checkpoints

Download model weights

Stop a running job

Delete a training job

List all trained models

​Job status lifecycle

​Start a training job

​List training jobs

​Get training job status

​Get training logs

​List checkpoints

​Download model weights

​Stop a running job

​Delete a training job

​List all trained models

Job status lifecycle

Start a training job

List training jobs

Get training job status

Get training logs

List checkpoints

Download model weights

Stop a running job

Delete a training job

List all trained models