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_0001_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: 0.27906976744186046
hushem_1x_deit_tiny_sgd_0001_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: 1.5555
- Accuracy: 0.2791
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: 0.0001
- 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 | 1.6995 | 0.2791 |
| 1.7242 | 2.0 | 12 | 1.6902 | 0.2791 |
| 1.7242 | 3.0 | 18 | 1.6819 | 0.2791 |
| 1.6909 | 4.0 | 24 | 1.6741 | 0.2791 |
| 1.6461 | 5.0 | 30 | 1.6664 | 0.2791 |
| 1.6461 | 6.0 | 36 | 1.6587 | 0.2791 |
| 1.6466 | 7.0 | 42 | 1.6518 | 0.2791 |
| 1.6466 | 8.0 | 48 | 1.6448 | 0.2791 |
| 1.6495 | 9.0 | 54 | 1.6384 | 0.2791 |
| 1.6495 | 10.0 | 60 | 1.6323 | 0.2791 |
| 1.6495 | 11.0 | 66 | 1.6267 | 0.2791 |
| 1.6244 | 12.0 | 72 | 1.6213 | 0.2791 |
| 1.6244 | 13.0 | 78 | 1.6166 | 0.2791 |
| 1.593 | 14.0 | 84 | 1.6117 | 0.2791 |
| 1.6183 | 15.0 | 90 | 1.6071 | 0.2791 |
| 1.6183 | 16.0 | 96 | 1.6026 | 0.2791 |
| 1.6105 | 17.0 | 102 | 1.5985 | 0.2558 |
| 1.6105 | 18.0 | 108 | 1.5946 | 0.2558 |
| 1.5599 | 19.0 | 114 | 1.5912 | 0.2558 |
| 1.5756 | 20.0 | 120 | 1.5878 | 0.2558 |
| 1.5756 | 21.0 | 126 | 1.5845 | 0.2558 |
| 1.5692 | 22.0 | 132 | 1.5817 | 0.2558 |
| 1.5692 | 23.0 | 138 | 1.5789 | 0.2558 |
| 1.544 | 24.0 | 144 | 1.5763 | 0.2558 |
| 1.548 | 25.0 | 150 | 1.5738 | 0.2558 |
| 1.548 | 26.0 | 156 | 1.5716 | 0.2791 |
| 1.549 | 27.0 | 162 | 1.5695 | 0.2791 |
| 1.549 | 28.0 | 168 | 1.5675 | 0.2791 |
| 1.5593 | 29.0 | 174 | 1.5658 | 0.2791 |
| 1.528 | 30.0 | 180 | 1.5641 | 0.2791 |
| 1.528 | 31.0 | 186 | 1.5627 | 0.2791 |
| 1.5394 | 32.0 | 192 | 1.5615 | 0.2791 |
| 1.5394 | 33.0 | 198 | 1.5603 | 0.2791 |
| 1.4822 | 34.0 | 204 | 1.5592 | 0.2791 |
| 1.5618 | 35.0 | 210 | 1.5583 | 0.2791 |
| 1.5618 | 36.0 | 216 | 1.5575 | 0.2791 |
| 1.5279 | 37.0 | 222 | 1.5568 | 0.2791 |
| 1.5279 | 38.0 | 228 | 1.5563 | 0.2791 |
| 1.5233 | 39.0 | 234 | 1.5559 | 0.2791 |
| 1.5255 | 40.0 | 240 | 1.5556 | 0.2791 |
| 1.5255 | 41.0 | 246 | 1.5555 | 0.2791 |
| 1.5147 | 42.0 | 252 | 1.5555 | 0.2791 |
| 1.5147 | 43.0 | 258 | 1.5555 | 0.2791 |
| 1.5048 | 44.0 | 264 | 1.5555 | 0.2791 |
| 1.5464 | 45.0 | 270 | 1.5555 | 0.2791 |
| 1.5464 | 46.0 | 276 | 1.5555 | 0.2791 |
| 1.5243 | 47.0 | 282 | 1.5555 | 0.2791 |
| 1.5243 | 48.0 | 288 | 1.5555 | 0.2791 |
| 1.5049 | 49.0 | 294 | 1.5555 | 0.2791 |
| 1.5545 | 50.0 | 300 | 1.5555 | 0.2791 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1