CV fine-tuning: trainer configuration
Now that you have prepared the dataset and adapted a pretrained model to the new classes, it is time to configure your trainer.
The TrainingArguments and Trainer have been loaded from the transformers library. The model (model) and dataset (dataset) have been loaded as you previously configured them.
Este exercício faz parte do curso
Multi-Modal Models with Hugging Face
Instruções do exercício
- Adjust the learning rate to
6e-5. - Provide the model, training data, and test data to the
Trainerinstance.
Exercício interativo prático
Experimente este exercício completando este código de exemplo.
training_args = TrainingArguments(
output_dir="dataset_finetune",
# Adjust the learning rate
____,
gradient_accumulation_steps=4,
num_train_epochs=3,
push_to_hub=False
)
trainer = Trainer(
# Provide the model and datasets
model=____,
args=training_args,
data_collator=data_collator,
train_dataset=____,
eval_dataset=____,
processing_class=image_processor,
compute_metrics=compute_metrics,
)