vit-base-patch16-224-U7-10
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7356
- Accuracy: 0.7833
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: 5.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3526 | 1.0 | 10 | 1.2843 | 0.4667 |
| 1.2233 | 2.0 | 20 | 1.1650 | 0.5833 |
| 1.1009 | 3.0 | 30 | 1.0405 | 0.65 |
| 0.9819 | 4.0 | 40 | 0.9573 | 0.65 |
| 0.8728 | 5.0 | 50 | 0.8657 | 0.6833 |
| 0.7702 | 6.0 | 60 | 0.8245 | 0.6667 |
| 0.7075 | 7.0 | 70 | 0.7998 | 0.7333 |
| 0.6324 | 8.0 | 80 | 0.8108 | 0.75 |
| 0.5928 | 9.0 | 90 | 0.7402 | 0.75 |
| 0.5649 | 10.0 | 100 | 0.7356 | 0.7833 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0