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_sgd_lr001_fold3
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: 0.4186046511627907
hushem_1x_deit_tiny_sgd_lr001_fold3
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: 1.3137
- Accuracy: 0.4186
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 | 1.5163 | 0.3023 |
| 1.6001 | 2.0 | 12 | 1.4936 | 0.3023 |
| 1.6001 | 3.0 | 18 | 1.4729 | 0.3023 |
| 1.5411 | 4.0 | 24 | 1.4550 | 0.3023 |
| 1.4977 | 5.0 | 30 | 1.4401 | 0.3023 |
| 1.4977 | 6.0 | 36 | 1.4267 | 0.3023 |
| 1.4396 | 7.0 | 42 | 1.4159 | 0.3023 |
| 1.4396 | 8.0 | 48 | 1.4066 | 0.3023 |
| 1.4314 | 9.0 | 54 | 1.3991 | 0.3023 |
| 1.3704 | 10.0 | 60 | 1.3909 | 0.3023 |
| 1.3704 | 11.0 | 66 | 1.3847 | 0.3023 |
| 1.3552 | 12.0 | 72 | 1.3793 | 0.3023 |
| 1.3552 | 13.0 | 78 | 1.3735 | 0.3256 |
| 1.3421 | 14.0 | 84 | 1.3686 | 0.3488 |
| 1.3202 | 15.0 | 90 | 1.3638 | 0.3488 |
| 1.3202 | 16.0 | 96 | 1.3593 | 0.3721 |
| 1.2948 | 17.0 | 102 | 1.3558 | 0.3953 |
| 1.2948 | 18.0 | 108 | 1.3518 | 0.3953 |
| 1.2928 | 19.0 | 114 | 1.3488 | 0.3953 |
| 1.2647 | 20.0 | 120 | 1.3454 | 0.3953 |
| 1.2647 | 21.0 | 126 | 1.3427 | 0.3953 |
| 1.2556 | 22.0 | 132 | 1.3402 | 0.3953 |
| 1.2556 | 23.0 | 138 | 1.3379 | 0.3953 |
| 1.253 | 24.0 | 144 | 1.3353 | 0.3953 |
| 1.2437 | 25.0 | 150 | 1.3327 | 0.3953 |
| 1.2437 | 26.0 | 156 | 1.3306 | 0.4186 |
| 1.2239 | 27.0 | 162 | 1.3289 | 0.3953 |
| 1.2239 | 28.0 | 168 | 1.3270 | 0.3953 |
| 1.2275 | 29.0 | 174 | 1.3251 | 0.3953 |
| 1.2028 | 30.0 | 180 | 1.3234 | 0.3953 |
| 1.2028 | 31.0 | 186 | 1.3221 | 0.3953 |
| 1.202 | 32.0 | 192 | 1.3205 | 0.3953 |
| 1.202 | 33.0 | 198 | 1.3191 | 0.3953 |
| 1.194 | 34.0 | 204 | 1.3178 | 0.3953 |
| 1.1993 | 35.0 | 210 | 1.3169 | 0.4186 |
| 1.1993 | 36.0 | 216 | 1.3160 | 0.4186 |
| 1.1904 | 37.0 | 222 | 1.3153 | 0.4186 |
| 1.1904 | 38.0 | 228 | 1.3147 | 0.4186 |
| 1.1785 | 39.0 | 234 | 1.3142 | 0.4186 |
| 1.2086 | 40.0 | 240 | 1.3139 | 0.4186 |
| 1.2086 | 41.0 | 246 | 1.3138 | 0.4186 |
| 1.1893 | 42.0 | 252 | 1.3137 | 0.4186 |
| 1.1893 | 43.0 | 258 | 1.3137 | 0.4186 |
| 1.2 | 44.0 | 264 | 1.3137 | 0.4186 |
| 1.1775 | 45.0 | 270 | 1.3137 | 0.4186 |
| 1.1775 | 46.0 | 276 | 1.3137 | 0.4186 |
| 1.1852 | 47.0 | 282 | 1.3137 | 0.4186 |
| 1.1852 | 48.0 | 288 | 1.3137 | 0.4186 |
| 1.1783 | 49.0 | 294 | 1.3137 | 0.4186 |
| 1.1702 | 50.0 | 300 | 1.3137 | 0.4186 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1