metadata
library_name: transformers
license: apache-2.0
base_model: facebook/deit-base-distilled-patch16-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deit-ena24
results: []
deit-ena24
This model is a fine-tuned version of facebook/deit-base-distilled-patch16-224 on the ena24 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0870
- Accuracy: 0.9794
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2994 | 0.1302 | 100 | 1.0314 | 0.7092 |
| 0.8789 | 0.2604 | 200 | 0.6169 | 0.8328 |
| 0.4592 | 0.3906 | 300 | 0.5234 | 0.8298 |
| 0.6806 | 0.5208 | 400 | 0.5431 | 0.8489 |
| 0.4878 | 0.6510 | 500 | 0.3905 | 0.8855 |
| 0.4643 | 0.7812 | 600 | 0.3281 | 0.9092 |
| 0.3765 | 0.9115 | 700 | 0.2398 | 0.9290 |
| 0.1379 | 1.0417 | 800 | 0.1861 | 0.9412 |
| 0.1422 | 1.1719 | 900 | 0.1657 | 0.9527 |
| 0.2655 | 1.3021 | 1000 | 0.1526 | 0.9557 |
| 0.0304 | 1.4323 | 1100 | 0.1578 | 0.9634 |
| 0.072 | 1.5625 | 1200 | 0.1418 | 0.9679 |
| 0.2936 | 1.6927 | 1300 | 0.1003 | 0.9771 |
| 0.0333 | 1.8229 | 1400 | 0.0935 | 0.9794 |
| 0.0844 | 1.9531 | 1500 | 0.0870 | 0.9794 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1