metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_deit_tiny_rms_001_fold1
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: 0.5555555555555556
hushem_40x_deit_tiny_rms_001_fold1
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: 7.3853
- Accuracy: 0.5556
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 |
|---|---|---|---|---|
| 1.1884 | 1.0 | 215 | 1.1880 | 0.4444 |
| 0.7323 | 2.0 | 430 | 1.1545 | 0.5111 |
| 0.6559 | 3.0 | 645 | 3.0305 | 0.3556 |
| 0.5702 | 4.0 | 860 | 1.2302 | 0.5111 |
| 0.5375 | 5.0 | 1075 | 2.2528 | 0.4222 |
| 0.4472 | 6.0 | 1290 | 1.9208 | 0.5111 |
| 0.4382 | 7.0 | 1505 | 1.8095 | 0.4889 |
| 0.3809 | 8.0 | 1720 | 2.0821 | 0.4222 |
| 0.3012 | 9.0 | 1935 | 1.8136 | 0.4 |
| 0.2478 | 10.0 | 2150 | 2.1397 | 0.4889 |
| 0.2029 | 11.0 | 2365 | 1.9762 | 0.5556 |
| 0.1971 | 12.0 | 2580 | 2.3756 | 0.5778 |
| 0.213 | 13.0 | 2795 | 1.6329 | 0.6444 |
| 0.1476 | 14.0 | 3010 | 2.7699 | 0.5333 |
| 0.098 | 15.0 | 3225 | 2.9763 | 0.5556 |
| 0.1482 | 16.0 | 3440 | 3.4825 | 0.5111 |
| 0.1197 | 17.0 | 3655 | 2.4388 | 0.6444 |
| 0.0935 | 18.0 | 3870 | 2.6931 | 0.5778 |
| 0.0698 | 19.0 | 4085 | 3.8147 | 0.5333 |
| 0.1713 | 20.0 | 4300 | 3.1091 | 0.5556 |
| 0.0331 | 21.0 | 4515 | 3.7485 | 0.5778 |
| 0.0687 | 22.0 | 4730 | 3.9845 | 0.5778 |
| 0.0351 | 23.0 | 4945 | 3.2773 | 0.6 |
| 0.0341 | 24.0 | 5160 | 4.2021 | 0.5333 |
| 0.0324 | 25.0 | 5375 | 6.0388 | 0.4889 |
| 0.022 | 26.0 | 5590 | 4.1761 | 0.6 |
| 0.1048 | 27.0 | 5805 | 2.9470 | 0.6 |
| 0.0202 | 28.0 | 6020 | 3.8209 | 0.5778 |
| 0.0085 | 29.0 | 6235 | 4.1758 | 0.5111 |
| 0.0013 | 30.0 | 6450 | 4.2128 | 0.5556 |
| 0.0026 | 31.0 | 6665 | 4.4304 | 0.4667 |
| 0.0003 | 32.0 | 6880 | 4.6210 | 0.5111 |
| 0.015 | 33.0 | 7095 | 3.7643 | 0.5556 |
| 0.0066 | 34.0 | 7310 | 4.8748 | 0.5778 |
| 0.0 | 35.0 | 7525 | 4.7438 | 0.5556 |
| 0.0 | 36.0 | 7740 | 5.0565 | 0.5111 |
| 0.0 | 37.0 | 7955 | 5.3178 | 0.5333 |
| 0.0 | 38.0 | 8170 | 5.6008 | 0.5333 |
| 0.0 | 39.0 | 8385 | 5.8863 | 0.5333 |
| 0.0 | 40.0 | 8600 | 6.1779 | 0.5333 |
| 0.0 | 41.0 | 8815 | 6.4282 | 0.5333 |
| 0.0 | 42.0 | 9030 | 6.6702 | 0.5556 |
| 0.0 | 43.0 | 9245 | 6.8800 | 0.5556 |
| 0.0 | 44.0 | 9460 | 7.0514 | 0.5556 |
| 0.0 | 45.0 | 9675 | 7.1938 | 0.5556 |
| 0.0 | 46.0 | 9890 | 7.2836 | 0.5556 |
| 0.0 | 47.0 | 10105 | 7.3402 | 0.5556 |
| 0.0 | 48.0 | 10320 | 7.3740 | 0.5556 |
| 0.0 | 49.0 | 10535 | 7.3831 | 0.5556 |
| 0.0 | 50.0 | 10750 | 7.3853 | 0.5556 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2