Scenario Model Stage Overview

⚠️

Check This First!

This article refers to BaseModel accessed via Docker container. Please refer to Snowflake Native App section if you are using BaseModel as SF GUI application.

The Foundation Model is designed to understand the behavior and interactions between entities and develop a general predictive capability in the domain. During training, it doesn’t have a more specific goal than that.

To address a particular business problem, you need to create a downstream model tailored to the scenario, by fine-tuning the Foundation Model for the specific task.

In this article we focus on that step:

To build a downstream model for their particular business objective, the user needs to adapt the training script template, and execute the training using a Python function or via the command line.

Any scenario training script contains the following elements:

from typing import Dict

import numpy as np

from monad.batch import SPLIT_TIMESTAMP
from monad.ui.config import TrainingParams
from monad.ui.module import MultilabelClassificationTask, load_from_foundation_model
from monad.ui.target_function import Attributes, Events, has_incomplete_training_window, next_n_days

TARGET_NAMES = ["sony", "apple"]
TARGET_ENTITY = "brand"

task = MultilabelClassificationTask(class_names=TARGET_NAMES)

def target_fn(_history: Events, future: Events, _entity: Attributes, _ctx: Dict) -> np.ndarray:
    target_window_days = 21
    if has_incomplete_training_window(_ctx, target_window_days):
        return None
    future = next_n_days(future, _ctx[SPLIT_TIMESTAMP], target_window_days)
    purchase_target, _ = future["transactions"].groupBy(TARGET_ENTITY).exists(groups=TARGET_NAMES)
    return purchase_target

fm_path = "/path/to/your/fm"

trainer = load_from_foundation_model(
    checkpoint_path=fm_path, 
    downstream_task=task, 
    target_fn=target_fn)

training_params = TrainingParams(
    learning_rate=0.0001,
    checkpoint_dir="/path/to/your/scenario/checkpoints",
    epochs=3
)

trainer.fit(training_params=training_params)

Given the breadth of the material, it has been divided into two sections:

1. Defining the Task and the Target:
   
   • Identify the machine learning problem:
     Determine the machine learning problem that aligns with the business objective.
   • Define the target function:
     Specify the function that will guide the model's optimization process.
     
2. Setting up the learning process:
   
   • Select the pre-trained Foundation Model:
     Point the script to the directory containing the features of the pre-trained model.
   • Configure the modelling task:
     Set up the downstream task and, if necessary, adjust the training parameters.
   • Instantiate the trainer:
     Create an instance of the trainer and, if needed, modify the loading process.
     

Follow the links above, or proceed to the following articles for detailed explanations of the above tasks.