List job

# Docs for v1 can be found by changing the above selector ^
from together import Together
import os

client = Together(
    api_key=os.environ.get("TOGETHER_API_KEY"),
)

fine_tune = client.fine_tuning.retrieve(id="ft-id")

print(fine_tune)

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "user_id": "<string>",
  "training_file": "<string>",
  "validation_file": "<string>",
  "model": "<string>",
  "model_output_name": "<string>",
  "model_output_path": "<string>",
  "model_object_id": "<string>",
  "model_object_revision_id": "<string>",
  "adapter_object_id": "<string>",
  "adapter_object_revision_id": "<string>",
  "trainingfile_numlines": 123,
  "trainingfile_size": 123,
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "started_at": "2023-11-07T05:31:56Z",
  "n_epochs": 123,
  "n_checkpoints": 123,
  "n_evals": 123,
  "batch_size": "max",
  "learning_rate": 123,
  "lr_scheduler": {
    "lr_scheduler_args": {
      "min_lr_ratio": 0
    }
  },
  "warmup_ratio": 123,
  "max_grad_norm": 123,
  "weight_decay": 123,
  "eval_steps": 123,
  "train_on_inputs": "auto",
  "training_method": {
    "method": "sft",
    "train_on_inputs": "auto"
  },
  "training_type": {
    "type": "Full"
  },
  "multimodal_params": {
    "train_vision": true
  },
  "job_id": "<string>",
  "events": [
    {
      "object": "<unknown>",
      "created_at": "<string>",
      "message": "<string>",
      "param_count": 123,
      "token_count": 123,
      "total_steps": 123,
      "wandb_url": "<string>",
      "step": 123,
      "checkpoint_path": "<string>",
      "model_path": "<string>",
      "early_stopping_best_step": 123,
      "early_stopping_best_metric_value": 123
    }
  ],
  "token_count": 123,
  "param_count": 123,
  "total_price": 123,
  "epochs_completed": 123,
  "queue_depth": 123,
  "wandb_project_name": "<string>",
  "wandb_url": "<string>",
  "from_checkpoint": "<string>",
  "from_hf_model": "<string>",
  "hf_model_revision": "<string>",
  "progress": {
    "estimate_available": true,
    "seconds_remaining": 123
  },
  "early_stopped": true,
  "early_stopping_best_step": 123,
  "early_stopping_best_metric": 123
}

GET

fine-tunes

{id}

# Docs for v1 can be found by changing the above selector ^
from together import Together
import os

client = Together(
    api_key=os.environ.get("TOGETHER_API_KEY"),
)

fine_tune = client.fine_tuning.retrieve(id="ft-id")

print(fine_tune)

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "user_id": "<string>",
  "training_file": "<string>",
  "validation_file": "<string>",
  "model": "<string>",
  "model_output_name": "<string>",
  "model_output_path": "<string>",
  "model_object_id": "<string>",
  "model_object_revision_id": "<string>",
  "adapter_object_id": "<string>",
  "adapter_object_revision_id": "<string>",
  "trainingfile_numlines": 123,
  "trainingfile_size": 123,
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "started_at": "2023-11-07T05:31:56Z",
  "n_epochs": 123,
  "n_checkpoints": 123,
  "n_evals": 123,
  "batch_size": "max",
  "learning_rate": 123,
  "lr_scheduler": {
    "lr_scheduler_args": {
      "min_lr_ratio": 0
    }
  },
  "warmup_ratio": 123,
  "max_grad_norm": 123,
  "weight_decay": 123,
  "eval_steps": 123,
  "train_on_inputs": "auto",
  "training_method": {
    "method": "sft",
    "train_on_inputs": "auto"
  },
  "training_type": {
    "type": "Full"
  },
  "multimodal_params": {
    "train_vision": true
  },
  "job_id": "<string>",
  "events": [
    {
      "object": "<unknown>",
      "created_at": "<string>",
      "message": "<string>",
      "param_count": 123,
      "token_count": 123,
      "total_steps": 123,
      "wandb_url": "<string>",
      "step": 123,
      "checkpoint_path": "<string>",
      "model_path": "<string>",
      "early_stopping_best_step": 123,
      "early_stopping_best_metric_value": 123
    }
  ],
  "token_count": 123,
  "param_count": 123,
  "total_price": 123,
  "epochs_completed": 123,
  "queue_depth": 123,
  "wandb_project_name": "<string>",
  "wandb_url": "<string>",
  "from_checkpoint": "<string>",
  "from_hf_model": "<string>",
  "hf_model_revision": "<string>",
  "progress": {
    "estimate_available": true,
    "seconds_remaining": 123
  },
  "early_stopped": true,
  "early_stopping_best_step": 123,
  "early_stopping_best_metric": 123
}

Authorizations

Authorization

string

header

default:default

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

string

required

The ID of the job to retrieve

Response

200 - application/json

Fine-tune job details retrieved successfully

string<uuid>

required

user_id

string

required

ID of the user who owns the fine-tune job.

status

enum<string>

required

Available options:

pending,

queued,

running,

compressing,

uploading,

cancel_requested,

cancelled,

error,

completed

training_file

string

validation_file

string

model

string

model_output_name

string

model_output_path

string

model_object_id

string

Together model registry object ID for the final model weights (e.g. ml_...).

model_object_revision_id

string

Together model registry revision ID for the final model weights (e.g. rv_...).

adapter_object_id

string

Together model registry object ID for the final adapter weights on LoRA jobs.

adapter_object_revision_id

string

Together model registry revision ID for the final adapter weights on LoRA jobs.

trainingfile_numlines

integer

trainingfile_size

integer

created_at

string<date-time>

updated_at

string<date-time>

started_at

string<date-time>

n_epochs

integer

n_checkpoints

integer

n_evals

integer

batch_size

default:max

learning_rate

number

lr_scheduler

object

Show child attributes

warmup_ratio

number

max_grad_norm

number

weight_decay

number

eval_steps

integer

train_on_inputs

default:auto

training_method

object

Option 1
Option 2

Show child attributes

training_type

object

Option 1
Option 2

Show child attributes

multimodal_params

object

Show child attributes

job_id

string

events

object[]

Show child attributes

token_count

integer

param_count

integer

total_price

integer

epochs_completed

integer

queue_depth

integer

wandb_project_name

string

wandb_url

string

from_checkpoint

string

from_hf_model

string

hf_model_revision

string

progress

object

Progress information for a fine-tuning job

Show child attributes

early_stopped

boolean

Whether the early-stopping criterion triggered.

early_stopping_best_step

integer

Step associated with the selected early-stopping artifact. When early_stopping_best_metric is null, no finite best metric was recorded; this is the halt step, not a best-checkpoint step.

early_stopping_best_metric

number | null

Best validation loss observed, corresponding to early_stopping_best_step. Null if no improving evaluation was recorded (for example, a non-finite first evaluation).

List all jobs

List job events

⌘I

TOGETHER APIS

SDK LIBRARIES

ERROR CODES

Authorizations

Path Parameters

Response