Downloads · 30 days
12
32% of all-time downloads
hushem_5x_deit_tiny_rms_00001_fold1
hkivancoral/hushem_5x_deit_tiny_rms_00001_fold1
hushem_5x_deit_tiny_rms_00001_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
38
Public
Parameters
5.5M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors22.1 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Nov 19, 2023
- Updated
- Nov 19, 2023
- SHA
- 5d13eaad
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_5x_deit_tiny_rms_00001_fold1
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3602
- Accuracy: 0.7778
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 |
|---|---|---|---|---|
| 0.9252 | 1.0 | 27 | 1.0120 | 0.5778 |
| 0.3509 | 2.0 | 54 | 1.1528 | 0.5111 |
| 0.157 | 3.0 | 81 | 0.9423 | 0.6 |
| 0.0726 | 4.0 | 108 | 0.9109 | 0.6889 |
| 0.0239 | 5.0 | 135 | 0.9135 | 0.6889 |
| 0.0054 | 6.0 | 162 | 1.0256 | 0.7111 |
| 0.0021 | 7.0 | 189 | 1.0270 | 0.7333 |
| 0.001 | 8.0 | 216 | 1.0391 | 0.7333 |
| 0.0007 | 9.0 | 243 | 1.0771 | 0.7333 |
| 0.0005 | 10.0 | 270 | 1.1362 | 0.7333 |
| 0.0004 | 11.0 | 297 | 1.1449 | 0.7333 |
| 0.0003 | 12.0 | 324 | 1.1213 | 0.7333 |
| 0.0003 | 13.0 | 351 | 1.1342 | 0.7333 |
| 0.0002 | 14.0 | 378 | 1.1386 | 0.7333 |
| 0.0002 | 15.0 | 405 | 1.1658 | 0.7333 |
| 0.0002 | 16.0 | 432 | 1.1625 | 0.7333 |
| 0.0002 | 17.0 | 459 | 1.1658 | 0.7333 |
| 0.0001 | 18.0 | 486 | 1.2038 | 0.7333 |
| 0.0001 | 19.0 | 513 | 1.1982 | 0.7333 |
| 0.0001 | 20.0 | 540 | 1.1900 | 0.7333 |
| 0.0001 | 21.0 | 567 | 1.2002 | 0.7333 |
| 0.0001 | 22.0 | 594 | 1.2242 | 0.7333 |
| 0.0001 | 23.0 | 621 | 1.2171 | 0.7333 |
| 0.0001 | 24.0 | 648 | 1.2379 | 0.7333 |
| 0.0001 | 25.0 | 675 | 1.2677 | 0.7556 |
| 0.0001 | 26.0 | 702 | 1.2348 | 0.7333 |
| 0.0 | 27.0 | 729 | 1.2383 | 0.7333 |
| 0.0 | 28.0 | 756 | 1.2522 | 0.7333 |
| 0.0 | 29.0 | 783 | 1.2632 | 0.7556 |
| 0.0 | 30.0 | 810 | 1.2618 | 0.7333 |
| 0.0 | 31.0 | 837 | 1.2923 | 0.7556 |
| 0.0 | 32.0 | 864 | 1.2897 | 0.7556 |
| 0.0 | 33.0 | 891 | 1.2981 | 0.7556 |
| 0.0 | 34.0 | 918 | 1.3107 | 0.7556 |
| 0.0 | 35.0 | 945 | 1.3012 | 0.7556 |
| 0.0 | 36.0 | 972 | 1.3267 | 0.7556 |
| 0.0 | 37.0 | 999 | 1.3179 | 0.7556 |
| 0.0 | 38.0 | 1026 | 1.3216 | 0.7556 |
| 0.0 | 39.0 | 1053 | 1.3292 | 0.7556 |
| 0.0 | 40.0 | 1080 | 1.3316 | 0.7778 |
| 0.0 | 41.0 | 1107 | 1.3369 | 0.7778 |
| 0.0 | 42.0 | 1134 | 1.3527 | 0.7778 |
| 0.0 | 43.0 | 1161 | 1.3532 | 0.7778 |
| 0.0 | 44.0 | 1188 | 1.3550 | 0.7778 |
| 0.0 | 45.0 | 1215 | 1.3537 | 0.7778 |
| 0.0 | 46.0 | 1242 | 1.3590 | 0.7778 |
| 0.0 | 47.0 | 1269 | 1.3613 | 0.7778 |
| 0.0 | 48.0 | 1296 | 1.3601 | 0.7778 |
| 0.0 | 49.0 | 1323 | 1.3602 | 0.7778 |
| 0.0 | 50.0 | 1350 | 1.3602 | 0.7778 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Nov 19, 2023
- Updated
- Nov 19, 2023