BaşlayınÜcretsiz başlayın

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.

Bu egzersiz, kursun bir parçasıdır

Multi-Modal Models with Hugging Face

Kursa Göz Atın

Egzersiz talimatları

  • Adjust the learning rate to 6e-5.
  • Provide the model, training data, and test data to the Trainer instance.

Uygulamalı etkileşimli egzersiz

Bu egzersizi bu örnek kodu tamamlayarak deneyin.

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,
)
Kodu Düzenle ve Çalıştır