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_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: 0.36585365853658536
hushem_1x_deit_tiny_sgd_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: 1.2764
- Accuracy: 0.3659
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 | 1.6481 | 0.2439 |
| 1.6453 | 2.0 | 12 | 1.5595 | 0.2439 |
| 1.6453 | 3.0 | 18 | 1.4979 | 0.2683 |
| 1.5144 | 4.0 | 24 | 1.4546 | 0.2683 |
| 1.4538 | 5.0 | 30 | 1.4262 | 0.2927 |
| 1.4538 | 6.0 | 36 | 1.4074 | 0.2683 |
| 1.3994 | 7.0 | 42 | 1.3954 | 0.2683 |
| 1.3994 | 8.0 | 48 | 1.3847 | 0.2683 |
| 1.3731 | 9.0 | 54 | 1.3749 | 0.2683 |
| 1.3564 | 10.0 | 60 | 1.3671 | 0.2927 |
| 1.3564 | 11.0 | 66 | 1.3612 | 0.3415 |
| 1.3402 | 12.0 | 72 | 1.3541 | 0.3659 |
| 1.3402 | 13.0 | 78 | 1.3472 | 0.3171 |
| 1.2912 | 14.0 | 84 | 1.3416 | 0.3171 |
| 1.304 | 15.0 | 90 | 1.3360 | 0.2927 |
| 1.304 | 16.0 | 96 | 1.3318 | 0.3171 |
| 1.267 | 17.0 | 102 | 1.3278 | 0.3171 |
| 1.267 | 18.0 | 108 | 1.3225 | 0.3171 |
| 1.2687 | 19.0 | 114 | 1.3187 | 0.3415 |
| 1.2447 | 20.0 | 120 | 1.3147 | 0.3415 |
| 1.2447 | 21.0 | 126 | 1.3131 | 0.3171 |
| 1.2262 | 22.0 | 132 | 1.3086 | 0.3171 |
| 1.2262 | 23.0 | 138 | 1.3054 | 0.3171 |
| 1.2132 | 24.0 | 144 | 1.3031 | 0.3171 |
| 1.2231 | 25.0 | 150 | 1.3007 | 0.3171 |
| 1.2231 | 26.0 | 156 | 1.2974 | 0.3171 |
| 1.1895 | 27.0 | 162 | 1.2937 | 0.3171 |
| 1.1895 | 28.0 | 168 | 1.2903 | 0.3415 |
| 1.2062 | 29.0 | 174 | 1.2886 | 0.3415 |
| 1.1907 | 30.0 | 180 | 1.2864 | 0.3415 |
| 1.1907 | 31.0 | 186 | 1.2852 | 0.3415 |
| 1.1836 | 32.0 | 192 | 1.2832 | 0.3415 |
| 1.1836 | 33.0 | 198 | 1.2819 | 0.3415 |
| 1.1632 | 34.0 | 204 | 1.2802 | 0.3415 |
| 1.1553 | 35.0 | 210 | 1.2792 | 0.3659 |
| 1.1553 | 36.0 | 216 | 1.2784 | 0.3659 |
| 1.1703 | 37.0 | 222 | 1.2777 | 0.3659 |
| 1.1703 | 38.0 | 228 | 1.2771 | 0.3659 |
| 1.1625 | 39.0 | 234 | 1.2768 | 0.3659 |
| 1.1523 | 40.0 | 240 | 1.2765 | 0.3659 |
| 1.1523 | 41.0 | 246 | 1.2764 | 0.3659 |
| 1.1617 | 42.0 | 252 | 1.2764 | 0.3659 |
| 1.1617 | 43.0 | 258 | 1.2764 | 0.3659 |
| 1.1427 | 44.0 | 264 | 1.2764 | 0.3659 |
| 1.1631 | 45.0 | 270 | 1.2764 | 0.3659 |
| 1.1631 | 46.0 | 276 | 1.2764 | 0.3659 |
| 1.162 | 47.0 | 282 | 1.2764 | 0.3659 |
| 1.162 | 48.0 | 288 | 1.2764 | 0.3659 |
| 1.1542 | 49.0 | 294 | 1.2764 | 0.3659 |
| 1.1633 | 50.0 | 300 | 1.2764 | 0.3659 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1