metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_1x_deit_tiny_adamax_001_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: 0.5777777777777777
hushem_1x_deit_tiny_adamax_001_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: 3.1828
- Accuracy: 0.5778
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: 0.001
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 6 | 1.5039 | 0.2444 |
| 1.9347 | 2.0 | 12 | 1.3951 | 0.2444 |
| 1.9347 | 3.0 | 18 | 1.5970 | 0.2444 |
| 1.3507 | 4.0 | 24 | 1.5883 | 0.2444 |
| 1.2448 | 5.0 | 30 | 1.2899 | 0.3111 |
| 1.2448 | 6.0 | 36 | 1.2061 | 0.3333 |
| 1.0721 | 7.0 | 42 | 1.5421 | 0.4444 |
| 1.0721 | 8.0 | 48 | 1.5331 | 0.2667 |
| 1.0322 | 9.0 | 54 | 1.2467 | 0.4889 |
| 1.0027 | 10.0 | 60 | 1.1754 | 0.4667 |
| 1.0027 | 11.0 | 66 | 1.3260 | 0.4444 |
| 0.8782 | 12.0 | 72 | 1.4220 | 0.3778 |
| 0.8782 | 13.0 | 78 | 1.2909 | 0.3778 |
| 0.9336 | 14.0 | 84 | 1.2228 | 0.3778 |
| 0.8518 | 15.0 | 90 | 1.3127 | 0.4889 |
| 0.8518 | 16.0 | 96 | 1.2461 | 0.5111 |
| 0.6856 | 17.0 | 102 | 1.5495 | 0.5111 |
| 0.6856 | 18.0 | 108 | 1.4003 | 0.4444 |
| 0.6629 | 19.0 | 114 | 1.6481 | 0.5111 |
| 0.6106 | 20.0 | 120 | 1.4665 | 0.5111 |
| 0.6106 | 21.0 | 126 | 1.3091 | 0.4667 |
| 0.5404 | 22.0 | 132 | 1.6995 | 0.5333 |
| 0.5404 | 23.0 | 138 | 1.3819 | 0.4889 |
| 0.6208 | 24.0 | 144 | 1.4295 | 0.4667 |
| 0.3803 | 25.0 | 150 | 1.5233 | 0.4667 |
| 0.3803 | 26.0 | 156 | 1.8157 | 0.5778 |
| 0.3131 | 27.0 | 162 | 1.2837 | 0.5556 |
| 0.3131 | 28.0 | 168 | 1.8123 | 0.5111 |
| 0.2542 | 29.0 | 174 | 1.9185 | 0.5333 |
| 0.1524 | 30.0 | 180 | 1.7784 | 0.6 |
| 0.1524 | 31.0 | 186 | 2.2830 | 0.5333 |
| 0.0946 | 32.0 | 192 | 2.4060 | 0.5556 |
| 0.0946 | 33.0 | 198 | 2.8614 | 0.4889 |
| 0.1333 | 34.0 | 204 | 2.7119 | 0.5333 |
| 0.1824 | 35.0 | 210 | 2.7486 | 0.4667 |
| 0.1824 | 36.0 | 216 | 2.8911 | 0.5556 |
| 0.0482 | 37.0 | 222 | 2.9042 | 0.5556 |
| 0.0482 | 38.0 | 228 | 2.8283 | 0.5778 |
| 0.0366 | 39.0 | 234 | 3.0321 | 0.5778 |
| 0.051 | 40.0 | 240 | 3.1410 | 0.5778 |
| 0.051 | 41.0 | 246 | 3.1802 | 0.5778 |
| 0.0414 | 42.0 | 252 | 3.1828 | 0.5778 |
| 0.0414 | 43.0 | 258 | 3.1828 | 0.5778 |
| 0.0218 | 44.0 | 264 | 3.1828 | 0.5778 |
| 0.0134 | 45.0 | 270 | 3.1828 | 0.5778 |
| 0.0134 | 46.0 | 276 | 3.1828 | 0.5778 |
| 0.0227 | 47.0 | 282 | 3.1828 | 0.5778 |
| 0.0227 | 48.0 | 288 | 3.1828 | 0.5778 |
| 0.0135 | 49.0 | 294 | 3.1828 | 0.5778 |
| 0.0221 | 50.0 | 300 | 3.1828 | 0.5778 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1