metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_3x_deit_small_sgd_00001_fold2
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: 0.4875207986688852
smids_3x_deit_small_sgd_00001_fold2
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: 1.0145
- Accuracy: 0.4875
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: 1e-05
- 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 |
|---|---|---|---|---|
| 1.0768 | 1.0 | 225 | 1.0706 | 0.4276 |
| 1.0941 | 2.0 | 450 | 1.0680 | 0.4293 |
| 1.0918 | 3.0 | 675 | 1.0655 | 0.4309 |
| 1.0511 | 4.0 | 900 | 1.0630 | 0.4376 |
| 1.0876 | 5.0 | 1125 | 1.0606 | 0.4393 |
| 1.0339 | 6.0 | 1350 | 1.0583 | 0.4393 |
| 1.0616 | 7.0 | 1575 | 1.0561 | 0.4459 |
| 1.0897 | 8.0 | 1800 | 1.0540 | 0.4459 |
| 1.053 | 9.0 | 2025 | 1.0518 | 0.4493 |
| 1.0515 | 10.0 | 2250 | 1.0498 | 0.4509 |
| 1.0879 | 11.0 | 2475 | 1.0479 | 0.4542 |
| 1.0316 | 12.0 | 2700 | 1.0459 | 0.4542 |
| 1.0424 | 13.0 | 2925 | 1.0441 | 0.4576 |
| 1.0786 | 14.0 | 3150 | 1.0424 | 0.4609 |
| 1.061 | 15.0 | 3375 | 1.0407 | 0.4626 |
| 1.064 | 16.0 | 3600 | 1.0390 | 0.4642 |
| 1.0184 | 17.0 | 3825 | 1.0374 | 0.4626 |
| 1.0313 | 18.0 | 4050 | 1.0359 | 0.4626 |
| 1.0429 | 19.0 | 4275 | 1.0344 | 0.4642 |
| 1.0308 | 20.0 | 4500 | 1.0330 | 0.4642 |
| 1.049 | 21.0 | 4725 | 1.0317 | 0.4659 |
| 1.0164 | 22.0 | 4950 | 1.0304 | 0.4642 |
| 1.0457 | 23.0 | 5175 | 1.0292 | 0.4642 |
| 1.0471 | 24.0 | 5400 | 1.0280 | 0.4626 |
| 1.0294 | 25.0 | 5625 | 1.0269 | 0.4642 |
| 1.0309 | 26.0 | 5850 | 1.0258 | 0.4659 |
| 1.0318 | 27.0 | 6075 | 1.0248 | 0.4659 |
| 1.0436 | 28.0 | 6300 | 1.0238 | 0.4676 |
| 1.0288 | 29.0 | 6525 | 1.0229 | 0.4725 |
| 1.0425 | 30.0 | 6750 | 1.0220 | 0.4742 |
| 1.0267 | 31.0 | 6975 | 1.0212 | 0.4792 |
| 1.0174 | 32.0 | 7200 | 1.0204 | 0.4809 |
| 1.0197 | 33.0 | 7425 | 1.0197 | 0.4809 |
| 1.0313 | 34.0 | 7650 | 1.0190 | 0.4809 |
| 1.0296 | 35.0 | 7875 | 1.0184 | 0.4809 |
| 1.0429 | 36.0 | 8100 | 1.0179 | 0.4842 |
| 1.0312 | 37.0 | 8325 | 1.0173 | 0.4859 |
| 1.0214 | 38.0 | 8550 | 1.0169 | 0.4842 |
| 1.0321 | 39.0 | 8775 | 1.0164 | 0.4859 |
| 1.0329 | 40.0 | 9000 | 1.0161 | 0.4859 |
| 1.0094 | 41.0 | 9225 | 1.0157 | 0.4875 |
| 0.9973 | 42.0 | 9450 | 1.0154 | 0.4875 |
| 1.0326 | 43.0 | 9675 | 1.0152 | 0.4875 |
| 1.0086 | 44.0 | 9900 | 1.0150 | 0.4875 |
| 1.0104 | 45.0 | 10125 | 1.0148 | 0.4875 |
| 1.0211 | 46.0 | 10350 | 1.0147 | 0.4875 |
| 0.9952 | 47.0 | 10575 | 1.0146 | 0.4875 |
| 0.9977 | 48.0 | 10800 | 1.0146 | 0.4875 |
| 1.0187 | 49.0 | 11025 | 1.0146 | 0.4875 |
| 1.0188 | 50.0 | 11250 | 1.0145 | 0.4875 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2