2025-01-21-16-13-04-vit-base-patch16-224
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: 0.0188
- Precision: 0.9929
- Recall: 0.9926
- F1: 0.9926
- Accuracy: 0.9931
- Top1 Accuracy: 0.9926
- Error Rate: 0.0069
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: 32
- eval_batch_size: 32
- seed: 3407
- 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 | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|---|---|---|---|---|---|---|---|---|---|
| 0.7465 | 1.0 | 34 | 0.1092 | 0.9536 | 0.9407 | 0.9400 | 0.9366 | 0.9407 | 0.0634 |
| 0.212 | 2.0 | 68 | 0.2754 | 0.9338 | 0.9111 | 0.9061 | 0.9049 | 0.9111 | 0.0951 |
| 0.115 | 3.0 | 102 | 0.0534 | 0.9854 | 0.9852 | 0.9852 | 0.9851 | 0.9852 | 0.0149 |
| 0.0723 | 4.0 | 136 | 0.0188 | 0.9929 | 0.9926 | 0.9926 | 0.9931 | 0.9926 | 0.0069 |
| 0.0716 | 5.0 | 170 | 0.0195 | 0.9928 | 0.9926 | 0.9926 | 0.992 | 0.9926 | 0.0080 |
| 0.0161 | 6.0 | 204 | 0.0389 | 0.9791 | 0.9778 | 0.9778 | 0.9775 | 0.9778 | 0.0225 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3