metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_small_rms_001_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: 0.5348837209302325
hushem_5x_deit_small_rms_001_fold3
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: 1.4338
- Accuracy: 0.5349
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 |
|---|---|---|---|---|
| 2.1632 | 1.0 | 28 | 2.6011 | 0.2558 |
| 1.512 | 2.0 | 56 | 1.9238 | 0.2558 |
| 1.4664 | 3.0 | 84 | 1.5930 | 0.2558 |
| 1.4243 | 4.0 | 112 | 1.6311 | 0.2558 |
| 1.4308 | 5.0 | 140 | 1.5023 | 0.2326 |
| 1.3985 | 6.0 | 168 | 1.3885 | 0.2326 |
| 1.6118 | 7.0 | 196 | 1.8250 | 0.2326 |
| 1.4607 | 8.0 | 224 | 1.4482 | 0.2558 |
| 1.4254 | 9.0 | 252 | 1.5210 | 0.2326 |
| 1.2281 | 10.0 | 280 | 1.2713 | 0.2791 |
| 1.1707 | 11.0 | 308 | 1.6980 | 0.3256 |
| 1.1948 | 12.0 | 336 | 1.3889 | 0.3488 |
| 1.0995 | 13.0 | 364 | 1.2122 | 0.4651 |
| 1.0119 | 14.0 | 392 | 1.2109 | 0.3721 |
| 1.025 | 15.0 | 420 | 1.1189 | 0.4419 |
| 0.9953 | 16.0 | 448 | 1.0970 | 0.5581 |
| 1.0322 | 17.0 | 476 | 1.1852 | 0.5581 |
| 1.0805 | 18.0 | 504 | 1.3503 | 0.4651 |
| 1.0129 | 19.0 | 532 | 1.0139 | 0.5581 |
| 0.8769 | 20.0 | 560 | 1.2502 | 0.5349 |
| 0.9527 | 21.0 | 588 | 0.9400 | 0.6977 |
| 0.8714 | 22.0 | 616 | 0.9462 | 0.6744 |
| 0.8727 | 23.0 | 644 | 1.1395 | 0.4419 |
| 0.8037 | 24.0 | 672 | 0.9359 | 0.5814 |
| 0.7753 | 25.0 | 700 | 0.7772 | 0.6047 |
| 0.8041 | 26.0 | 728 | 0.7536 | 0.6744 |
| 0.8222 | 27.0 | 756 | 1.0294 | 0.4186 |
| 0.7867 | 28.0 | 784 | 1.0146 | 0.6512 |
| 0.7746 | 29.0 | 812 | 1.1197 | 0.5116 |
| 0.6826 | 30.0 | 840 | 0.8534 | 0.6977 |
| 0.6952 | 31.0 | 868 | 0.9094 | 0.5814 |
| 0.7133 | 32.0 | 896 | 0.7819 | 0.6047 |
| 0.6818 | 33.0 | 924 | 0.8848 | 0.6977 |
| 0.634 | 34.0 | 952 | 1.0225 | 0.6047 |
| 0.7437 | 35.0 | 980 | 0.9642 | 0.5349 |
| 0.6195 | 36.0 | 1008 | 1.1344 | 0.6047 |
| 0.6464 | 37.0 | 1036 | 1.0624 | 0.4186 |
| 0.5946 | 38.0 | 1064 | 1.1057 | 0.5116 |
| 0.5887 | 39.0 | 1092 | 1.0910 | 0.6512 |
| 0.6287 | 40.0 | 1120 | 1.0898 | 0.5581 |
| 0.5714 | 41.0 | 1148 | 1.2124 | 0.5349 |
| 0.5356 | 42.0 | 1176 | 1.2782 | 0.5116 |
| 0.4544 | 43.0 | 1204 | 1.1905 | 0.5814 |
| 0.3966 | 44.0 | 1232 | 1.4293 | 0.5349 |
| 0.3676 | 45.0 | 1260 | 1.3361 | 0.5581 |
| 0.3673 | 46.0 | 1288 | 1.3624 | 0.5349 |
| 0.3108 | 47.0 | 1316 | 1.3804 | 0.5581 |
| 0.2776 | 48.0 | 1344 | 1.4296 | 0.5349 |
| 0.2985 | 49.0 | 1372 | 1.4338 | 0.5349 |
| 0.271 | 50.0 | 1400 | 1.4338 | 0.5349 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0