metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-masaratti
results: []
vit-base-patch16-224-masaratti
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2993
- Accuracy: 0.8806
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6663 | 1.0 | 10 | 0.8463 | 0.6269 |
| 0.4895 | 2.0 | 20 | 0.6918 | 0.6940 |
| 0.3694 | 3.0 | 30 | 0.5267 | 0.7612 |
| 0.2751 | 4.0 | 40 | 0.3793 | 0.8433 |
| 0.2724 | 5.0 | 50 | 0.4968 | 0.7836 |
| 0.1872 | 6.0 | 60 | 0.2743 | 0.9030 |
| 0.1388 | 7.0 | 70 | 0.3087 | 0.8657 |
| 0.1249 | 8.0 | 80 | 0.2829 | 0.8731 |
| 0.1006 | 9.0 | 90 | 0.3123 | 0.8881 |
| 0.0973 | 10.0 | 100 | 0.2993 | 0.8806 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1