metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_tiny_adamax_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: 0.7777777777777778
hushem_5x_deit_tiny_adamax_00001_fold2
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: 1.3029
- Accuracy: 0.7778
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: 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 |
|---|---|---|---|---|
| 0.7446 | 1.0 | 27 | 0.9312 | 0.6667 |
| 0.1747 | 2.0 | 54 | 1.0634 | 0.6667 |
| 0.0436 | 3.0 | 81 | 1.1538 | 0.6889 |
| 0.0072 | 4.0 | 108 | 1.1186 | 0.7111 |
| 0.0036 | 5.0 | 135 | 1.4466 | 0.6667 |
| 0.0007 | 6.0 | 162 | 1.3997 | 0.6889 |
| 0.0023 | 7.0 | 189 | 1.1775 | 0.7333 |
| 0.0002 | 8.0 | 216 | 1.3345 | 0.7333 |
| 0.0001 | 9.0 | 243 | 1.2661 | 0.7333 |
| 0.0001 | 10.0 | 270 | 1.2707 | 0.7333 |
| 0.0001 | 11.0 | 297 | 1.2671 | 0.7333 |
| 0.0001 | 12.0 | 324 | 1.2637 | 0.7556 |
| 0.0001 | 13.0 | 351 | 1.2664 | 0.7556 |
| 0.0001 | 14.0 | 378 | 1.2658 | 0.7556 |
| 0.0001 | 15.0 | 405 | 1.2627 | 0.7556 |
| 0.0001 | 16.0 | 432 | 1.2685 | 0.7556 |
| 0.0001 | 17.0 | 459 | 1.2678 | 0.7778 |
| 0.0001 | 18.0 | 486 | 1.2674 | 0.7778 |
| 0.0001 | 19.0 | 513 | 1.2701 | 0.7778 |
| 0.0001 | 20.0 | 540 | 1.2690 | 0.7778 |
| 0.0001 | 21.0 | 567 | 1.2702 | 0.7778 |
| 0.0 | 22.0 | 594 | 1.2727 | 0.7778 |
| 0.0 | 23.0 | 621 | 1.2744 | 0.7778 |
| 0.0 | 24.0 | 648 | 1.2792 | 0.7778 |
| 0.0 | 25.0 | 675 | 1.2781 | 0.7778 |
| 0.0 | 26.0 | 702 | 1.2815 | 0.7778 |
| 0.0 | 27.0 | 729 | 1.2813 | 0.7778 |
| 0.0 | 28.0 | 756 | 1.2838 | 0.7778 |
| 0.0 | 29.0 | 783 | 1.2855 | 0.7778 |
| 0.0 | 30.0 | 810 | 1.2884 | 0.7778 |
| 0.0 | 31.0 | 837 | 1.2896 | 0.7778 |
| 0.0 | 32.0 | 864 | 1.2918 | 0.7778 |
| 0.0 | 33.0 | 891 | 1.2896 | 0.7778 |
| 0.0 | 34.0 | 918 | 1.2932 | 0.7778 |
| 0.0 | 35.0 | 945 | 1.2947 | 0.7778 |
| 0.0 | 36.0 | 972 | 1.2919 | 0.7778 |
| 0.0 | 37.0 | 999 | 1.2951 | 0.7778 |
| 0.0 | 38.0 | 1026 | 1.2979 | 0.7778 |
| 0.0 | 39.0 | 1053 | 1.3002 | 0.7778 |
| 0.0 | 40.0 | 1080 | 1.2989 | 0.7778 |
| 0.0 | 41.0 | 1107 | 1.3009 | 0.7778 |
| 0.0 | 42.0 | 1134 | 1.3017 | 0.7778 |
| 0.0 | 43.0 | 1161 | 1.3020 | 0.7778 |
| 0.0 | 44.0 | 1188 | 1.3018 | 0.7778 |
| 0.0 | 45.0 | 1215 | 1.3024 | 0.7778 |
| 0.0 | 46.0 | 1242 | 1.3027 | 0.7778 |
| 0.0 | 47.0 | 1269 | 1.3028 | 0.7778 |
| 0.0 | 48.0 | 1296 | 1.3029 | 0.7778 |
| 0.0 | 49.0 | 1323 | 1.3029 | 0.7778 |
| 0.0 | 50.0 | 1350 | 1.3029 | 0.7778 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0