vit_base_aihub_model_py
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0228
- Accuracy: 0.9978
- Precision: 0.9981
- Recall: 0.9974
- F1: 0.9978
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.1415 | 1.0 | 149 | 0.1286 | 0.9712 | 0.9788 | 0.9623 | 0.9700 |
| 0.0671 | 2.0 | 299 | 0.0463 | 0.9948 | 0.9917 | 0.9946 | 0.9932 |
| 0.0423 | 3.0 | 448 | 0.0356 | 0.9952 | 0.9970 | 0.9908 | 0.9939 |
| 0.0383 | 4.0 | 598 | 0.0242 | 0.9976 | 0.9980 | 0.9972 | 0.9976 |
| 0.033 | 4.98 | 745 | 0.0228 | 0.9978 | 0.9981 | 0.9974 | 0.9978 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3