Downloads · 30 days
3
2% of all-time downloads
smids_3x_deit_base_rms_00001_fold2
hkivancoral/smids_3x_deit_base_rms_00001_fold2
smids_3x_deit_base_rms_00001_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
197
Public
Repo size
17.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Dec 12, 2023
- Updated
- Dec 12, 2023
- SHA
- f3787114
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. -->
smids_3x_deit_base_rms_00001_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: 1.1006
- Accuracy: 0.8802
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 |
|---|---|---|---|---|
| 0.1997 | 1.0 | 225 | 0.3294 | 0.8636 |
| 0.1218 | 2.0 | 450 | 0.3458 | 0.8752 |
| 0.0584 | 3.0 | 675 | 0.3858 | 0.8852 |
| 0.0328 | 4.0 | 900 | 0.5094 | 0.8819 |
| 0.0105 | 5.0 | 1125 | 0.6264 | 0.8669 |
| 0.0195 | 6.0 | 1350 | 0.6524 | 0.8819 |
| 0.0393 | 7.0 | 1575 | 0.7580 | 0.8785 |
| 0.0118 | 8.0 | 1800 | 0.8225 | 0.8752 |
| 0.0025 | 9.0 | 2025 | 0.8445 | 0.8885 |
| 0.0015 | 10.0 | 2250 | 0.9017 | 0.8752 |
| 0.0012 | 11.0 | 2475 | 0.8480 | 0.8885 |
| 0.0006 | 12.0 | 2700 | 0.8747 | 0.8802 |
| 0.0003 | 13.0 | 2925 | 0.8028 | 0.8819 |
| 0.0034 | 14.0 | 3150 | 0.8751 | 0.8769 |
| 0.0001 | 15.0 | 3375 | 0.8609 | 0.8852 |
| 0.0001 | 16.0 | 3600 | 0.9267 | 0.8769 |
| 0.0057 | 17.0 | 3825 | 0.9169 | 0.8735 |
| 0.036 | 18.0 | 4050 | 0.8611 | 0.8885 |
| 0.0 | 19.0 | 4275 | 0.8854 | 0.8785 |
| 0.0034 | 20.0 | 4500 | 1.0598 | 0.8669 |
| 0.0 | 21.0 | 4725 | 0.9577 | 0.8752 |
| 0.0 | 22.0 | 4950 | 0.9365 | 0.8686 |
| 0.0032 | 23.0 | 5175 | 0.9251 | 0.8785 |
| 0.0 | 24.0 | 5400 | 0.9847 | 0.8686 |
| 0.0035 | 25.0 | 5625 | 1.0144 | 0.8719 |
| 0.0 | 26.0 | 5850 | 1.0411 | 0.8636 |
| 0.0 | 27.0 | 6075 | 1.0565 | 0.8669 |
| 0.0 | 28.0 | 6300 | 1.0364 | 0.8702 |
| 0.0 | 29.0 | 6525 | 1.0760 | 0.8785 |
| 0.003 | 30.0 | 6750 | 1.0560 | 0.8785 |
| 0.0 | 31.0 | 6975 | 0.9941 | 0.8835 |
| 0.0 | 32.0 | 7200 | 1.0698 | 0.8735 |
| 0.0 | 33.0 | 7425 | 1.0500 | 0.8769 |
| 0.0 | 34.0 | 7650 | 0.9900 | 0.8852 |
| 0.0 | 35.0 | 7875 | 1.1120 | 0.8735 |
| 0.0032 | 36.0 | 8100 | 1.0645 | 0.8819 |
| 0.0 | 37.0 | 8325 | 1.0762 | 0.8802 |
| 0.0 | 38.0 | 8550 | 1.0820 | 0.8819 |
| 0.0032 | 39.0 | 8775 | 1.0824 | 0.8769 |
| 0.0 | 40.0 | 9000 | 1.0804 | 0.8769 |
| 0.0 | 41.0 | 9225 | 1.0824 | 0.8785 |
| 0.0 | 42.0 | 9450 | 1.0865 | 0.8819 |
| 0.0 | 43.0 | 9675 | 1.0882 | 0.8802 |
| 0.0 | 44.0 | 9900 | 1.0914 | 0.8802 |
| 0.0 | 45.0 | 10125 | 1.0895 | 0.8819 |
| 0.0 | 46.0 | 10350 | 1.0934 | 0.8819 |
| 0.0 | 47.0 | 10575 | 1.0962 | 0.8819 |
| 0.0 | 48.0 | 10800 | 1.0971 | 0.8819 |
| 0.0022 | 49.0 | 11025 | 1.0991 | 0.8802 |
| 0.0022 | 50.0 | 11250 | 1.1006 | 0.8802 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Dec 12, 2023
- Updated
- Dec 12, 2023