metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: deit-tiny-patch16-224-RESISC45_01
results: []
deit-tiny-patch16-224-RESISC45_01
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3266
- Accuracy: 0.912
- Precision: 0.9184
- Recall: 0.912
- F1: 0.9127
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: 0.0001
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 2.1588 | 1.0 | 37 | 1.4843 | 0.716 | 0.7429 | 0.716 | 0.7079 |
| 1.1043 | 2.0 | 74 | 0.8240 | 0.825 | 0.8391 | 0.825 | 0.8245 |
| 0.801 | 3.0 | 111 | 0.5870 | 0.866 | 0.8733 | 0.866 | 0.8660 |
| 0.6546 | 4.0 | 148 | 0.4760 | 0.885 | 0.8916 | 0.885 | 0.8852 |
| 0.5632 | 5.0 | 185 | 0.4202 | 0.896 | 0.9038 | 0.896 | 0.8963 |
| 0.5004 | 6.0 | 222 | 0.3792 | 0.895 | 0.9046 | 0.895 | 0.8953 |
| 0.4392 | 7.0 | 259 | 0.3483 | 0.906 | 0.9126 | 0.906 | 0.9067 |
| 0.4358 | 8.0 | 296 | 0.3436 | 0.907 | 0.9150 | 0.907 | 0.9084 |
| 0.4208 | 9.0 | 333 | 0.3298 | 0.908 | 0.9135 | 0.908 | 0.9086 |
| 0.4148 | 10.0 | 370 | 0.3266 | 0.912 | 0.9184 | 0.912 | 0.9127 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1