Create a fine tuning job

POST 
/ai/fine_tuning/jobs

Create a new fine tuning job.

application/json

Body

required

model stringrequired

The base model that is being fine-tuned.

training_file stringrequired

The storage bucket or object used for training.

suffix string

Optional suffix to append to the fine tuned model's name.

hyperparameters

object

The hyperparameters used for the fine-tuning job.

n_epochs integer

Possible values: >= 1 and <= 10

Default value: 3

The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. 'auto' decides the optimal number of epochs based on the size of the dataset. If setting the number manually, we support any number between 1 and 50 epochs.

The hyperparameters used for the fine-tuning job.

200: Successful Response

application/json

• Schema
• Example (from schema)

Schema

id stringrequired

The name of the fine-tuned model that is being created.

created_at integerrequired

The Unix timestamp (in seconds) for when the fine-tuning job was created.

finished_at integernullablerequired

The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running.

hyperparameters

object

required

The hyperparameters used for the fine-tuning job.

n_epochs integerrequired

Possible values: >= 1 and <= 10

Default value: 3

The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset.

The hyperparameters used for the fine-tuning job.

model stringrequired

The base model that is being fine-tuned.

organization_id stringrequired

The organization that owns the fine-tuning job.

status stringrequired

Possible values: [queued, running, succeeded, failed, cancelled]

The current status of the fine-tuning job.

trained_tokens integernullablerequired

The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.

training_file stringrequired

The storage bucket or object used for training.

{
  "id": "string",
  "created_at": 0,
  "finished_at": 0,
  "hyperparameters": {
    "n_epochs": 3
  },
  "model": "string",
  "organization_id": "string",
  "status": "queued",
  "trained_tokens": 0,
  "training_file": "string"
}

422: Validation Error

application/json

• Schema
• Example (from schema)

Schema

detail

object[]

Array [

loc

object[]

required

Array [

anyOf

• MOD1
• MOD2

string

integer

]

msg Message (string)required

type Error Type (string)required

]

{
  "detail": [
    {
      "loc": [
        "string",
        0
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

Request samples

• cURL

---

curl -L 'https://api.telnyx.com/v2/ai/fine_tuning/jobs' \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer <TOKEN>' \
-d '{
  "model": "string",
  "training_file": "string",
  "suffix": "string",
  "hyperparameters": {
    "n_epochs": 3
  }
}'

Response samples

• 200
• 422

---

{
  "id": "string",
  "created_at": 0,
  "finished_at": 0,
  "hyperparameters": {
    "n_epochs": 3
  },
  "model": "string",
  "organization_id": "string",
  "status": "queued",
  "trained_tokens": 0,
  "training_file": "string"
}

{
  "detail": [
    {
      "loc": [
        "string",
        0
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}