Downloads · 30 days
15
18% of all-time downloads
hushem_1x_deit_base_sgd_001_fold2
hkivancoral/hushem_1x_deit_base_sgd_001_fold2
hushem_1x_deit_base_sgd_001_fold2 is a image classification model from hkivancoral. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
83
Public
Parameters
85.8M
7.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Nov 15, 2023
- Updated
- Nov 15, 2023
- SHA
- 398e30d6
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
hushem_1x_deit_base_sgd_001_fold2
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3798
- Accuracy: 0.2
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 | 1.4713 | 0.1333 |
| 1.4188 | 2.0 | 12 | 1.4634 | 0.1333 |
| 1.4188 | 3.0 | 18 | 1.4564 | 0.1333 |
| 1.4085 | 4.0 | 24 | 1.4508 | 0.1333 |
| 1.3911 | 5.0 | 30 | 1.4443 | 0.1333 |
| 1.3911 | 6.0 | 36 | 1.4385 | 0.1333 |
| 1.3816 | 7.0 | 42 | 1.4335 | 0.1333 |
| 1.3816 | 8.0 | 48 | 1.4295 | 0.1111 |
| 1.3793 | 9.0 | 54 | 1.4254 | 0.1111 |
| 1.3554 | 10.0 | 60 | 1.4214 | 0.1111 |
| 1.3554 | 11.0 | 66 | 1.4179 | 0.1111 |
| 1.3538 | 12.0 | 72 | 1.4149 | 0.1111 |
| 1.3538 | 13.0 | 78 | 1.4119 | 0.1333 |
| 1.3412 | 14.0 | 84 | 1.4092 | 0.1333 |
| 1.3299 | 15.0 | 90 | 1.4068 | 0.1333 |
| 1.3299 | 16.0 | 96 | 1.4046 | 0.1333 |
| 1.3323 | 17.0 | 102 | 1.4026 | 0.1333 |
| 1.3323 | 18.0 | 108 | 1.4005 | 0.1556 |
| 1.3314 | 19.0 | 114 | 1.3985 | 0.1556 |
| 1.319 | 20.0 | 120 | 1.3965 | 0.1778 |
| 1.319 | 21.0 | 126 | 1.3949 | 0.1556 |
| 1.3167 | 22.0 | 132 | 1.3934 | 0.1556 |
| 1.3167 | 23.0 | 138 | 1.3918 | 0.1556 |
| 1.3277 | 24.0 | 144 | 1.3905 | 0.1556 |
| 1.3028 | 25.0 | 150 | 1.3894 | 0.1556 |
| 1.3028 | 26.0 | 156 | 1.3882 | 0.1556 |
| 1.305 | 27.0 | 162 | 1.3873 | 0.1556 |
| 1.305 | 28.0 | 168 | 1.3863 | 0.1778 |
| 1.2998 | 29.0 | 174 | 1.3854 | 0.2 |
| 1.2987 | 30.0 | 180 | 1.3845 | 0.2 |
| 1.2987 | 31.0 | 186 | 1.3838 | 0.1778 |
| 1.2931 | 32.0 | 192 | 1.3831 | 0.1778 |
| 1.2931 | 33.0 | 198 | 1.3824 | 0.1778 |
| 1.3006 | 34.0 | 204 | 1.3818 | 0.1778 |
| 1.2837 | 35.0 | 210 | 1.3813 | 0.2 |
| 1.2837 | 36.0 | 216 | 1.3809 | 0.2 |
| 1.2882 | 37.0 | 222 | 1.3806 | 0.2 |
| 1.2882 | 38.0 | 228 | 1.3803 | 0.2 |
| 1.2892 | 39.0 | 234 | 1.3801 | 0.2 |
| 1.288 | 40.0 | 240 | 1.3799 | 0.2 |
| 1.288 | 41.0 | 246 | 1.3798 | 0.2 |
| 1.2923 | 42.0 | 252 | 1.3798 | 0.2 |
| 1.2923 | 43.0 | 258 | 1.3798 | 0.2 |
| 1.2814 | 44.0 | 264 | 1.3798 | 0.2 |
| 1.291 | 45.0 | 270 | 1.3798 | 0.2 |
| 1.291 | 46.0 | 276 | 1.3798 | 0.2 |
| 1.2879 | 47.0 | 282 | 1.3798 | 0.2 |
| 1.2879 | 48.0 | 288 | 1.3798 | 0.2 |
| 1.2801 | 49.0 | 294 | 1.3798 | 0.2 |
| 1.2884 | 50.0 | 300 | 1.3798 | 0.2 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Nov 15, 2023
- Updated
- Nov 15, 2023