Start Training
Start a new model fine-tuning job using the Knowledgator Python SDK.
Configuration Template
When starting a training job, specify your target base model, training dataset, and optional hyperparameters:
model_id("<BASE_MODEL_ID>"): The base model to fine-tune. Options include"comprehend-it"(zero-shot text classification and NLI),"gliclass-x-base"(general entity/token classification), or any model identifier returned bykg.finetuning.list_models().dataset_id("<DATASET_ID>"): The unique UUID of your training dataset (e.g."6babd48a-2256-4466-b16b-9fd45ba59688"), obtained fromkg.datasets.list()or after uploading viakg.datasets.create().hyperparameters: Optional dictionary of training arguments (learning_rate,batch_size,epochs,seed).
from knowledgator import Knowledgator
kg = Knowledgator(api_key="YOUR_API_KEY")
training = kg.finetuning.start_training(
model_id="<BASE_MODEL_ID>",
dataset_id="<DATASET_ID>",
hyperparameters={
"learning_rate": 0.0001,
"batch_size": 16,
"epochs": 5
}
)
Concrete Example
Fine-tuning the comprehend-it base model using an uploaded dataset:
from knowledgator import Knowledgator
kg = Knowledgator(api_key="YOUR_API_KEY")
training = kg.finetuning.start_training(
model_id="comprehend-it",
dataset_id="6babd48a-2256-4466-b16b-9fd45ba59688",
hyperparameters={
"learning_rate": 0.0001,
"batch_size": 16,
"epochs": 5
}
)
print(training.id, training.status)
Expected Output
78d379da228a4985ba19100f53245b79 pending
Result Object Structure
{
"id": "78d379da228a4985ba19100f53245b79",
"model_id": "comprehend-it",
"dataset_id": "6babd48a-2256-4466-b16b-9fd45ba59688",
"status": "pending",
"type": "model",
"created_at": "2024-02-15T09:00:00Z"
}