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_rms_001_fold5
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: 0.6097560975609756
hushem_1x_deit_tiny_rms_001_fold5
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: 1.1358
- Accuracy: 0.6098
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 | 4.7231 | 0.2683 |
| 4.2141 | 2.0 | 12 | 1.8531 | 0.2683 |
| 4.2141 | 3.0 | 18 | 1.6449 | 0.2439 |
| 1.9845 | 4.0 | 24 | 1.4265 | 0.2439 |
| 1.5807 | 5.0 | 30 | 2.0165 | 0.2439 |
| 1.5807 | 6.0 | 36 | 1.5975 | 0.2683 |
| 1.5979 | 7.0 | 42 | 1.4305 | 0.3171 |
| 1.5979 | 8.0 | 48 | 1.4587 | 0.2683 |
| 1.4992 | 9.0 | 54 | 1.2917 | 0.3171 |
| 1.4954 | 10.0 | 60 | 1.2462 | 0.4390 |
| 1.4954 | 11.0 | 66 | 1.2479 | 0.2683 |
| 1.415 | 12.0 | 72 | 1.1246 | 0.5122 |
| 1.415 | 13.0 | 78 | 1.1689 | 0.4878 |
| 1.374 | 14.0 | 84 | 1.3767 | 0.2927 |
| 1.3675 | 15.0 | 90 | 1.1692 | 0.4146 |
| 1.3675 | 16.0 | 96 | 1.6528 | 0.2927 |
| 1.319 | 17.0 | 102 | 1.3151 | 0.3659 |
| 1.319 | 18.0 | 108 | 1.1475 | 0.4146 |
| 1.3335 | 19.0 | 114 | 1.1506 | 0.3415 |
| 1.2819 | 20.0 | 120 | 1.2300 | 0.3902 |
| 1.2819 | 21.0 | 126 | 1.1641 | 0.4146 |
| 1.2507 | 22.0 | 132 | 1.4148 | 0.3659 |
| 1.2507 | 23.0 | 138 | 1.3061 | 0.3415 |
| 1.2134 | 24.0 | 144 | 1.2367 | 0.3415 |
| 1.2611 | 25.0 | 150 | 1.2383 | 0.4878 |
| 1.2611 | 26.0 | 156 | 1.0375 | 0.4878 |
| 1.2053 | 27.0 | 162 | 1.1983 | 0.4878 |
| 1.2053 | 28.0 | 168 | 1.1898 | 0.4146 |
| 1.1593 | 29.0 | 174 | 1.1479 | 0.4878 |
| 1.2426 | 30.0 | 180 | 1.1382 | 0.5610 |
| 1.2426 | 31.0 | 186 | 1.0558 | 0.5610 |
| 1.1866 | 32.0 | 192 | 1.1895 | 0.4390 |
| 1.1866 | 33.0 | 198 | 1.2172 | 0.4146 |
| 1.1453 | 34.0 | 204 | 1.3773 | 0.4146 |
| 1.1026 | 35.0 | 210 | 1.1168 | 0.5122 |
| 1.1026 | 36.0 | 216 | 1.1184 | 0.5610 |
| 1.131 | 37.0 | 222 | 1.1344 | 0.5366 |
| 1.131 | 38.0 | 228 | 1.0932 | 0.5122 |
| 1.1098 | 39.0 | 234 | 1.1070 | 0.6098 |
| 1.0797 | 40.0 | 240 | 1.1237 | 0.5854 |
| 1.0797 | 41.0 | 246 | 1.1366 | 0.6098 |
| 1.0648 | 42.0 | 252 | 1.1358 | 0.6098 |
| 1.0648 | 43.0 | 258 | 1.1358 | 0.6098 |
| 1.0281 | 44.0 | 264 | 1.1358 | 0.6098 |
| 1.0542 | 45.0 | 270 | 1.1358 | 0.6098 |
| 1.0542 | 46.0 | 276 | 1.1358 | 0.6098 |
| 1.0409 | 47.0 | 282 | 1.1358 | 0.6098 |
| 1.0409 | 48.0 | 288 | 1.1358 | 0.6098 |
| 1.0504 | 49.0 | 294 | 1.1358 | 0.6098 |
| 1.0111 | 50.0 | 300 | 1.1358 | 0.6098 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1