Downloads · 30 days
19
12% of all-time downloads
hushem_5x_deit_base_rms_0001_fold1
hkivancoral/hushem_5x_deit_base_rms_0001_fold1
hushem_5x_deit_base_rms_0001_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
155
Public
Parameters
85.8M
16.8 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 24, 2023
- Updated
- Nov 24, 2023
- SHA
- 7d5e1218
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_rms_0001_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: 1.9961
- Accuracy: 0.7111
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: 0.0001
- 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 |
|---|---|---|---|---|
| 1.4401 | 1.0 | 27 | 1.3889 | 0.2444 |
| 1.4795 | 2.0 | 54 | 1.6032 | 0.2444 |
| 1.2229 | 3.0 | 81 | 1.1436 | 0.5111 |
| 0.8987 | 4.0 | 108 | 1.0040 | 0.5556 |
| 0.4853 | 5.0 | 135 | 1.0534 | 0.6222 |
| 0.1456 | 6.0 | 162 | 1.8360 | 0.5556 |
| 0.0696 | 7.0 | 189 | 1.2156 | 0.7333 |
| 0.0874 | 8.0 | 216 | 0.7950 | 0.7556 |
| 0.0365 | 9.0 | 243 | 1.6830 | 0.7111 |
| 0.0006 | 10.0 | 270 | 1.6730 | 0.7111 |
| 0.0002 | 11.0 | 297 | 1.6991 | 0.7111 |
| 0.0002 | 12.0 | 324 | 1.7182 | 0.7111 |
| 0.0001 | 13.0 | 351 | 1.7320 | 0.7111 |
| 0.0001 | 14.0 | 378 | 1.7414 | 0.7111 |
| 0.0001 | 15.0 | 405 | 1.7505 | 0.7111 |
| 0.0001 | 16.0 | 432 | 1.7579 | 0.7111 |
| 0.0001 | 17.0 | 459 | 1.7666 | 0.7111 |
| 0.0001 | 18.0 | 486 | 1.7749 | 0.7111 |
| 0.0001 | 19.0 | 513 | 1.7836 | 0.7333 |
| 0.0 | 20.0 | 540 | 1.7919 | 0.7333 |
| 0.0 | 21.0 | 567 | 1.8002 | 0.7111 |
| 0.0 | 22.0 | 594 | 1.8101 | 0.7111 |
| 0.0 | 23.0 | 621 | 1.8191 | 0.7111 |
| 0.0 | 24.0 | 648 | 1.8264 | 0.7111 |
| 0.0 | 25.0 | 675 | 1.8362 | 0.7111 |
| 0.0 | 26.0 | 702 | 1.8441 | 0.7111 |
| 0.0 | 27.0 | 729 | 1.8521 | 0.7111 |
| 0.0 | 28.0 | 756 | 1.8613 | 0.7111 |
| 0.0 | 29.0 | 783 | 1.8701 | 0.7111 |
| 0.0 | 30.0 | 810 | 1.8780 | 0.7111 |
| 0.0 | 31.0 | 837 | 1.8862 | 0.7111 |
| 0.0 | 32.0 | 864 | 1.8953 | 0.7111 |
| 0.0 | 33.0 | 891 | 1.9042 | 0.7111 |
| 0.0 | 34.0 | 918 | 1.9125 | 0.7111 |
| 0.0 | 35.0 | 945 | 1.9206 | 0.7111 |
| 0.0 | 36.0 | 972 | 1.9289 | 0.7111 |
| 0.0 | 37.0 | 999 | 1.9371 | 0.7111 |
| 0.0 | 38.0 | 1026 | 1.9452 | 0.7111 |
| 0.0 | 39.0 | 1053 | 1.9530 | 0.7111 |
| 0.0 | 40.0 | 1080 | 1.9602 | 0.7111 |
| 0.0 | 41.0 | 1107 | 1.9674 | 0.7111 |
| 0.0 | 42.0 | 1134 | 1.9741 | 0.7111 |
| 0.0 | 43.0 | 1161 | 1.9798 | 0.7111 |
| 0.0 | 44.0 | 1188 | 1.9852 | 0.7111 |
| 0.0 | 45.0 | 1215 | 1.9896 | 0.7111 |
| 0.0 | 46.0 | 1242 | 1.9931 | 0.7111 |
| 0.0 | 47.0 | 1269 | 1.9953 | 0.7111 |
| 0.0 | 48.0 | 1296 | 1.9961 | 0.7111 |
| 0.0 | 49.0 | 1323 | 1.9961 | 0.7111 |
| 0.0 | 50.0 | 1350 | 1.9961 | 0.7111 |
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 24, 2023
- Updated
- Nov 24, 2023