NInixtla

Foundational Time Series Model Multi Series Finetuning

Changed on

Fine-tune the large time model to your data and save it for later use. It takes a JSON as an input containing information like the series frequency and historical data. (See below for a full description of the parameters.) The response contains the ID of the finetuned model, which you can provide in other endpoints to use that model to make the forecasts. Get your token at https://nixtla.io/free-trial?utm_source=nixtla.io&utm_campaign=/docs/api-reference.

post/v2/finetune

Request

  • Base URL
    https://api.nixtla.io
  • Auth
    HTTP bearer

Request body

freqstring required

The frequency of the data represented as a string. 'D' for daily, 'M' for monthly, 'H' for hourly, and 'W' for weekly frequencies are available.

modelstring

Model to use as a string. Common options are (but not restricted to) timegpt-1 and timegpt-1-long-horizon. Full options vary by different users. Contact support@nixtla.io for more information. We recommend using timegpt-1-long-horizon for forecasting if you want to predict more than one seasonal period given the frequency of your data.

finetune_stepsinteger

The number of tuning steps used to train the large time model on the data. Set this value to 0 for zero-shot inference, i.e., to make predictions without any further model tuning.

finetune_loss'default' | 'mae' | 'mse' | 'rmse' | 'mape' | 'smape' | 'poisson'

The loss used to train the large time model on the data. Select from ['default', 'mae', 'mse', 'rmse', 'mape', 'smape', 'poisson']. It will only be used if finetune_steps is larger than 0. Default is a robust loss function that is less sensitive to outliers.

finetune_depth1 | 2 | 3 | 4 | 5

The depth of the finetuning. Uses a scale from 1 to 5, where 1 means little finetuning, and 5 means that the entire model is finetuned. Note that this parameter is only effective for timegpt-1 and timegpt-1-long-horizon models; it has no effect on the other models. By default, the value is set to 1.

output_model_idstring nullable

ID to assign to the finetuned model

finetuned_model_idstring nullable

ID of previously finetuned model

hist_exoginteger[] nullable

Zero-based indices of the exogenous features to treat as historical.

multivariateboolean

Compute multivariate predictions across a batch of multiple time series. Requires all time series with overlapping dates. Note that this is only effective for timegpt-2.1 model and it has no effect on the other models. By default, the value is set to False.

model_parametersobject nullable

Optional dictionary of parameters to customize the behavior of the large time model.

Response

Successful Response

input_tokensinteger required
output_tokensinteger required
finetune_tokensinteger required
finetuned_model_idstring required

Changes

  • 015ac23a238aRevision changes
    • info

      added the new optional request property /

  • 9da3f4939623Revision changes
    • breaking

      the request property type changed from no type to string

    • warning

      the request property's min was set to 0.00

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property /

    • info

      added the new optional request property /

    • info

      added the new optional request property /

    • info

      added the optional property // to the response with the status

    • info

      added the optional property // to the response with the status