Hugging Face Multi-Label Classification Training
Learn about the hf_clf_multi_label_train function within Simplifine’s Train Engine
hf_clf_multi_label_train(
model_name:str,
dataset_name:str='',
num_epochs:int=3,
batch_size:int=8,
lr:float=5e-5,
from_hf:bool=True,
inputs:list=[],
labels:list=[],
use_peft:bool=False,
peft_config=None,
accelerator=None,
apply_class_weights:bool=False,
num_labels:int=0
)
The name or path of the pre-trained model to use.
The name of the dataset to be used for training. Defaults to an empty string.
The number of training epochs. Defaults to 3.
The batch size for training. Defaults to 8.
The learning rate for optimization. Defaults to 5e-5.
A flag to determine whether to load the dataset from Hugging Face. Defaults to True.
A list of input data for training. Defaults to an empty list.
A list of labels for training. Defaults to an empty list.
A flag to enable Parameter-Efficient Fine-Tuning (PEFT). Defaults to False.
The configuration object for PEFT. Defaults to None.
The accelerator object for distributed training. Defaults to None.
A flag to apply class weights to handle imbalanced datasets. Defaults to False.
The number of labels in the dataset. Defaults to 0.