hushem_40x_deit_tiny_f1
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6177
- Accuracy: 0.8444
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: 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 |
|---|---|---|---|---|
| 0.1057 | 1.0 | 107 | 0.4673 | 0.8222 |
| 0.0156 | 2.0 | 214 | 0.4217 | 0.8667 |
| 0.0006 | 2.99 | 321 | 0.3052 | 0.8889 |
| 0.0004 | 4.0 | 429 | 0.7953 | 0.8222 |
| 0.0004 | 5.0 | 536 | 0.2677 | 0.8667 |
| 0.0001 | 6.0 | 643 | 0.5139 | 0.8444 |
| 0.0 | 6.99 | 750 | 0.5825 | 0.8444 |
| 0.0 | 8.0 | 858 | 0.6043 | 0.8444 |
| 0.0 | 9.0 | 965 | 0.6155 | 0.8444 |
| 0.0 | 9.98 | 1070 | 0.6177 | 0.8444 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1