metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_3x_deit_small_rms_00001_fold2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8685524126455907
smids_3x_deit_small_rms_00001_fold2
This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.2809
- Accuracy: 0.8686
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2767 | 1.0 | 225 | 0.3185 | 0.8686 |
| 0.1511 | 2.0 | 450 | 0.3126 | 0.8669 |
| 0.096 | 3.0 | 675 | 0.3591 | 0.8735 |
| 0.0576 | 4.0 | 900 | 0.4235 | 0.8735 |
| 0.0262 | 5.0 | 1125 | 0.4922 | 0.8819 |
| 0.0164 | 6.0 | 1350 | 0.6380 | 0.8719 |
| 0.0169 | 7.0 | 1575 | 0.7607 | 0.8569 |
| 0.0085 | 8.0 | 1800 | 0.8747 | 0.8602 |
| 0.0061 | 9.0 | 2025 | 0.9757 | 0.8586 |
| 0.002 | 10.0 | 2250 | 1.0480 | 0.8586 |
| 0.0017 | 11.0 | 2475 | 0.9765 | 0.8702 |
| 0.0016 | 12.0 | 2700 | 0.9383 | 0.8719 |
| 0.0018 | 13.0 | 2925 | 0.9688 | 0.8719 |
| 0.0 | 14.0 | 3150 | 0.9770 | 0.8602 |
| 0.0002 | 15.0 | 3375 | 0.9981 | 0.8686 |
| 0.0 | 16.0 | 3600 | 0.9902 | 0.8735 |
| 0.0075 | 17.0 | 3825 | 1.0861 | 0.8586 |
| 0.0092 | 18.0 | 4050 | 1.0830 | 0.8552 |
| 0.0002 | 19.0 | 4275 | 0.9892 | 0.8719 |
| 0.0029 | 20.0 | 4500 | 1.1768 | 0.8619 |
| 0.0 | 21.0 | 4725 | 1.1820 | 0.8619 |
| 0.031 | 22.0 | 4950 | 1.0285 | 0.8619 |
| 0.0053 | 23.0 | 5175 | 1.0925 | 0.8569 |
| 0.0 | 24.0 | 5400 | 1.1089 | 0.8652 |
| 0.0412 | 25.0 | 5625 | 1.2047 | 0.8502 |
| 0.0 | 26.0 | 5850 | 1.1861 | 0.8569 |
| 0.0 | 27.0 | 6075 | 1.2680 | 0.8569 |
| 0.0001 | 28.0 | 6300 | 1.1737 | 0.8652 |
| 0.0173 | 29.0 | 6525 | 1.2944 | 0.8486 |
| 0.0044 | 30.0 | 6750 | 1.1884 | 0.8636 |
| 0.0 | 31.0 | 6975 | 1.2534 | 0.8652 |
| 0.0 | 32.0 | 7200 | 1.2427 | 0.8636 |
| 0.0 | 33.0 | 7425 | 1.2253 | 0.8719 |
| 0.0 | 34.0 | 7650 | 1.2543 | 0.8652 |
| 0.0 | 35.0 | 7875 | 1.2431 | 0.8702 |
| 0.004 | 36.0 | 8100 | 1.2651 | 0.8619 |
| 0.0 | 37.0 | 8325 | 1.2443 | 0.8652 |
| 0.0 | 38.0 | 8550 | 1.2852 | 0.8669 |
| 0.004 | 39.0 | 8775 | 1.2690 | 0.8686 |
| 0.0 | 40.0 | 9000 | 1.2725 | 0.8686 |
| 0.0 | 41.0 | 9225 | 1.2668 | 0.8719 |
| 0.0 | 42.0 | 9450 | 1.2758 | 0.8686 |
| 0.0 | 43.0 | 9675 | 1.2725 | 0.8669 |
| 0.0 | 44.0 | 9900 | 1.2814 | 0.8669 |
| 0.0 | 45.0 | 10125 | 1.2808 | 0.8686 |
| 0.0 | 46.0 | 10350 | 1.2792 | 0.8702 |
| 0.0 | 47.0 | 10575 | 1.2803 | 0.8686 |
| 0.0 | 48.0 | 10800 | 1.2804 | 0.8686 |
| 0.0022 | 49.0 | 11025 | 1.2805 | 0.8686 |
| 0.0022 | 50.0 | 11250 | 1.2809 | 0.8686 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2