beans-deit-tiny-patch16-224
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.0576
- Accuracy: 0.9774
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3159 | 1.0 | 130 | 0.2388 | 0.9173 |
| 0.2644 | 2.0 | 260 | 0.1986 | 0.9323 |
| 0.18 | 3.0 | 390 | 0.0875 | 0.9774 |
| 0.1356 | 4.0 | 520 | 0.1328 | 0.9549 |
| 0.2743 | 5.0 | 650 | 0.0844 | 0.9699 |
| 0.0601 | 6.0 | 780 | 0.0722 | 0.9774 |
| 0.0679 | 7.0 | 910 | 0.0805 | 0.9699 |
| 0.1452 | 8.0 | 1040 | 0.0576 | 0.9774 |
| 0.0451 | 9.0 | 1170 | 0.0706 | 0.9774 |
| 0.1342 | 10.0 | 1300 | 0.0724 | 0.9774 |
Framework versions
- Transformers 4.38.0
- Pytorch 2.1.2+cu118
- Datasets 2.19.1
- Tokenizers 0.15.2
- Downloads last month
- 7
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for pkr7098/beans-deit-tiny-patch16-224
Base model
facebook/deit-tiny-patch16-224