Downloads · 30 days
11
3% of all-time downloads
hushem_40x_deit_small_adamax_001_fold1
hkivancoral/hushem_40x_deit_small_adamax_001_fold1
hushem_40x_deit_small_adamax_001_fold1 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
403
Public
Repo size
4.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin86.7 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Dec 24, 2023
- Updated
- Dec 24, 2023
- SHA
- 586a0aa3
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_40x_deit_small_adamax_001_fold1
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: 2.1541
- Accuracy: 0.7556
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 |
|---|---|---|---|---|
| 0.1447 | 1.0 | 215 | 1.0279 | 0.7556 |
| 0.0939 | 2.0 | 430 | 1.6244 | 0.7333 |
| 0.025 | 3.0 | 645 | 1.1738 | 0.8 |
| 0.0505 | 4.0 | 860 | 1.8318 | 0.6667 |
| 0.02 | 5.0 | 1075 | 1.9882 | 0.7333 |
| 0.1072 | 6.0 | 1290 | 1.2076 | 0.7333 |
| 0.0633 | 7.0 | 1505 | 1.6747 | 0.7333 |
| 0.0604 | 8.0 | 1720 | 1.1018 | 0.8 |
| 0.0484 | 9.0 | 1935 | 2.2857 | 0.6444 |
| 0.0045 | 10.0 | 2150 | 2.0338 | 0.7556 |
| 0.0317 | 11.0 | 2365 | 2.1474 | 0.7556 |
| 0.0239 | 12.0 | 2580 | 1.5303 | 0.7778 |
| 0.0001 | 13.0 | 2795 | 2.3569 | 0.6444 |
| 0.0001 | 14.0 | 3010 | 2.2079 | 0.7556 |
| 0.0 | 15.0 | 3225 | 1.6648 | 0.7778 |
| 0.0065 | 16.0 | 3440 | 1.7779 | 0.7778 |
| 0.0 | 17.0 | 3655 | 1.9802 | 0.7556 |
| 0.0 | 18.0 | 3870 | 2.1669 | 0.7778 |
| 0.0001 | 19.0 | 4085 | 1.9508 | 0.8 |
| 0.0 | 20.0 | 4300 | 3.0396 | 0.6889 |
| 0.0 | 21.0 | 4515 | 1.8449 | 0.7333 |
| 0.0 | 22.0 | 4730 | 1.8614 | 0.7333 |
| 0.0 | 23.0 | 4945 | 1.8711 | 0.7333 |
| 0.0 | 24.0 | 5160 | 1.8758 | 0.7333 |
| 0.0 | 25.0 | 5375 | 1.8839 | 0.7333 |
| 0.0 | 26.0 | 5590 | 1.8890 | 0.7111 |
| 0.0 | 27.0 | 5805 | 1.8959 | 0.7111 |
| 0.0 | 28.0 | 6020 | 1.9021 | 0.7111 |
| 0.0 | 29.0 | 6235 | 1.9100 | 0.7111 |
| 0.0 | 30.0 | 6450 | 1.9180 | 0.7111 |
| 0.0 | 31.0 | 6665 | 1.9279 | 0.7111 |
| 0.0 | 32.0 | 6880 | 1.9382 | 0.7333 |
| 0.0 | 33.0 | 7095 | 1.9497 | 0.7333 |
| 0.0 | 34.0 | 7310 | 1.9619 | 0.7333 |
| 0.0 | 35.0 | 7525 | 1.9743 | 0.7333 |
| 0.0 | 36.0 | 7740 | 1.9878 | 0.7333 |
| 0.0 | 37.0 | 7955 | 2.0026 | 0.7333 |
| 0.0 | 38.0 | 8170 | 2.0159 | 0.7333 |
| 0.0 | 39.0 | 8385 | 2.0312 | 0.7333 |
| 0.0 | 40.0 | 8600 | 2.0457 | 0.7333 |
| 0.0 | 41.0 | 8815 | 2.0615 | 0.7333 |
| 0.0 | 42.0 | 9030 | 2.0758 | 0.7333 |
| 0.0 | 43.0 | 9245 | 2.0899 | 0.7333 |
| 0.0 | 44.0 | 9460 | 2.1029 | 0.7333 |
| 0.0 | 45.0 | 9675 | 2.1161 | 0.7333 |
| 0.0 | 46.0 | 9890 | 2.1279 | 0.7556 |
| 0.0 | 47.0 | 10105 | 2.1385 | 0.7556 |
| 0.0 | 48.0 | 10320 | 2.1469 | 0.7556 |
| 0.0 | 49.0 | 10535 | 2.1525 | 0.7556 |
| 0.0 | 50.0 | 10750 | 2.1541 | 0.7556 |
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 24, 2023
- Updated
- Dec 24, 2023