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_sgd_00001_fold4
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: 0.2857142857142857
hushem_5x_deit_small_sgd_00001_fold4
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: 1.4657
- Accuracy: 0.2857
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 |
|---|---|---|---|---|
| 1.5422 | 1.0 | 28 | 1.4834 | 0.2619 |
| 1.6237 | 2.0 | 56 | 1.4826 | 0.2619 |
| 1.5562 | 3.0 | 84 | 1.4817 | 0.2619 |
| 1.5833 | 4.0 | 112 | 1.4810 | 0.2619 |
| 1.5467 | 5.0 | 140 | 1.4803 | 0.2619 |
| 1.5372 | 6.0 | 168 | 1.4795 | 0.2857 |
| 1.5683 | 7.0 | 196 | 1.4788 | 0.2857 |
| 1.5057 | 8.0 | 224 | 1.4781 | 0.2857 |
| 1.5994 | 9.0 | 252 | 1.4774 | 0.2857 |
| 1.5076 | 10.0 | 280 | 1.4768 | 0.2857 |
| 1.5466 | 11.0 | 308 | 1.4762 | 0.2857 |
| 1.544 | 12.0 | 336 | 1.4756 | 0.2857 |
| 1.5866 | 13.0 | 364 | 1.4750 | 0.2857 |
| 1.5384 | 14.0 | 392 | 1.4744 | 0.2857 |
| 1.6111 | 15.0 | 420 | 1.4739 | 0.2857 |
| 1.5625 | 16.0 | 448 | 1.4733 | 0.2857 |
| 1.547 | 17.0 | 476 | 1.4728 | 0.2857 |
| 1.5362 | 18.0 | 504 | 1.4723 | 0.2857 |
| 1.5318 | 19.0 | 532 | 1.4718 | 0.2857 |
| 1.5453 | 20.0 | 560 | 1.4714 | 0.2857 |
| 1.5434 | 21.0 | 588 | 1.4709 | 0.2857 |
| 1.548 | 22.0 | 616 | 1.4705 | 0.2857 |
| 1.5105 | 23.0 | 644 | 1.4701 | 0.2857 |
| 1.5176 | 24.0 | 672 | 1.4697 | 0.2857 |
| 1.5194 | 25.0 | 700 | 1.4694 | 0.2857 |
| 1.5543 | 26.0 | 728 | 1.4690 | 0.2857 |
| 1.5727 | 27.0 | 756 | 1.4687 | 0.2857 |
| 1.5476 | 28.0 | 784 | 1.4684 | 0.2857 |
| 1.5163 | 29.0 | 812 | 1.4681 | 0.2857 |
| 1.4767 | 30.0 | 840 | 1.4678 | 0.2857 |
| 1.5623 | 31.0 | 868 | 1.4676 | 0.2857 |
| 1.4924 | 32.0 | 896 | 1.4674 | 0.2857 |
| 1.5673 | 33.0 | 924 | 1.4672 | 0.2857 |
| 1.4842 | 34.0 | 952 | 1.4670 | 0.2857 |
| 1.4908 | 35.0 | 980 | 1.4668 | 0.2857 |
| 1.5184 | 36.0 | 1008 | 1.4666 | 0.2857 |
| 1.5315 | 37.0 | 1036 | 1.4664 | 0.2857 |
| 1.4892 | 38.0 | 1064 | 1.4663 | 0.2857 |
| 1.5241 | 39.0 | 1092 | 1.4662 | 0.2857 |
| 1.5587 | 40.0 | 1120 | 1.4661 | 0.2857 |
| 1.5867 | 41.0 | 1148 | 1.4660 | 0.2857 |
| 1.5357 | 42.0 | 1176 | 1.4659 | 0.2857 |
| 1.479 | 43.0 | 1204 | 1.4659 | 0.2857 |
| 1.4798 | 44.0 | 1232 | 1.4658 | 0.2857 |
| 1.5998 | 45.0 | 1260 | 1.4658 | 0.2857 |
| 1.5487 | 46.0 | 1288 | 1.4658 | 0.2857 |
| 1.5234 | 47.0 | 1316 | 1.4657 | 0.2857 |
| 1.5142 | 48.0 | 1344 | 1.4657 | 0.2857 |
| 1.5259 | 49.0 | 1372 | 1.4657 | 0.2857 |
| 1.5344 | 50.0 | 1400 | 1.4657 | 0.2857 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0