Downloads · 30 days
23
6% of all-time downloads
hushem_5x_deit_base_sgd_00001_fold1
hkivancoral/hushem_5x_deit_base_sgd_00001_fold1
hushem_5x_deit_base_sgd_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
401
Public
Parameters
85.8M
33.6 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 26, 2023
- Updated
- Nov 27, 2023
- SHA
- 23c192f7
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_base_sgd_00001_fold1
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: 1.4547
- 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: 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 |
|---|---|---|---|---|
| 1.4142 | 1.0 | 27 | 1.4588 | 0.2 |
| 1.43 | 2.0 | 54 | 1.4586 | 0.2 |
| 1.431 | 3.0 | 81 | 1.4584 | 0.2 |
| 1.428 | 4.0 | 108 | 1.4582 | 0.2 |
| 1.4298 | 5.0 | 135 | 1.4581 | 0.2 |
| 1.4162 | 6.0 | 162 | 1.4579 | 0.2 |
| 1.4151 | 7.0 | 189 | 1.4577 | 0.2 |
| 1.4305 | 8.0 | 216 | 1.4576 | 0.2 |
| 1.4174 | 9.0 | 243 | 1.4574 | 0.2 |
| 1.4253 | 10.0 | 270 | 1.4573 | 0.2 |
| 1.413 | 11.0 | 297 | 1.4571 | 0.2 |
| 1.4424 | 12.0 | 324 | 1.4570 | 0.2 |
| 1.4176 | 13.0 | 351 | 1.4569 | 0.2 |
| 1.4068 | 14.0 | 378 | 1.4567 | 0.2 |
| 1.4121 | 15.0 | 405 | 1.4566 | 0.2 |
| 1.4414 | 16.0 | 432 | 1.4565 | 0.2 |
| 1.4193 | 17.0 | 459 | 1.4564 | 0.2 |
| 1.4027 | 18.0 | 486 | 1.4563 | 0.2 |
| 1.4234 | 19.0 | 513 | 1.4561 | 0.2 |
| 1.4191 | 20.0 | 540 | 1.4560 | 0.2 |
| 1.422 | 21.0 | 567 | 1.4559 | 0.2 |
| 1.4308 | 22.0 | 594 | 1.4558 | 0.2 |
| 1.4159 | 23.0 | 621 | 1.4557 | 0.2 |
| 1.3917 | 24.0 | 648 | 1.4557 | 0.2 |
| 1.4256 | 25.0 | 675 | 1.4556 | 0.2 |
| 1.4297 | 26.0 | 702 | 1.4555 | 0.2 |
| 1.4255 | 27.0 | 729 | 1.4554 | 0.2 |
| 1.4283 | 28.0 | 756 | 1.4553 | 0.2 |
| 1.4093 | 29.0 | 783 | 1.4553 | 0.2 |
| 1.4375 | 30.0 | 810 | 1.4552 | 0.2 |
| 1.4191 | 31.0 | 837 | 1.4551 | 0.2 |
| 1.4114 | 32.0 | 864 | 1.4551 | 0.2 |
| 1.4302 | 33.0 | 891 | 1.4550 | 0.2 |
| 1.4246 | 34.0 | 918 | 1.4550 | 0.2 |
| 1.4179 | 35.0 | 945 | 1.4549 | 0.2 |
| 1.4054 | 36.0 | 972 | 1.4549 | 0.2 |
| 1.4083 | 37.0 | 999 | 1.4549 | 0.2 |
| 1.4246 | 38.0 | 1026 | 1.4548 | 0.2 |
| 1.4277 | 39.0 | 1053 | 1.4548 | 0.2 |
| 1.4249 | 40.0 | 1080 | 1.4548 | 0.2 |
| 1.4275 | 41.0 | 1107 | 1.4547 | 0.2 |
| 1.42 | 42.0 | 1134 | 1.4547 | 0.2 |
| 1.4184 | 43.0 | 1161 | 1.4547 | 0.2 |
| 1.3982 | 44.0 | 1188 | 1.4547 | 0.2 |
| 1.4187 | 45.0 | 1215 | 1.4547 | 0.2 |
| 1.4142 | 46.0 | 1242 | 1.4547 | 0.2 |
| 1.4272 | 47.0 | 1269 | 1.4547 | 0.2 |
| 1.4241 | 48.0 | 1296 | 1.4547 | 0.2 |
| 1.4142 | 49.0 | 1323 | 1.4547 | 0.2 |
| 1.4153 | 50.0 | 1350 | 1.4547 | 0.2 |
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 26, 2023
- Updated
- Nov 27, 2023