Downloads · 30 days
31
9% of all-time downloads
swiftformer-xs-RD-da-colab
Augusto777/swiftformer-xs-RD-da-colab
swiftformer-xs-RD-da-colab is a image classification model from Augusto777. Use it when you need a label for an image. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
364
Public
Parameters
3M
552 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors12.2 MB · 99%
At a glance
- Task
- Image Classification
- Library
- transformers
- Model type
- swiftformer
- Access
- Public
- Created
- Dec 9, 2024
- Updated
- Dec 9, 2024
- SHA
- 55f33730
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. -->
swiftformer-xs-RD-da-colab
This model is a fine-tuned version of MBZUAI/swiftformer-xs on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 5.5780
- Accuracy: 0.5018
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5414 | 1.0 | 96 | 9.3183 | 0.4945 |
| 0.533 | 2.0 | 192 | 7.8263 | 0.5 |
| 0.3449 | 3.0 | 288 | 8.6048 | 0.4945 |
| 0.3157 | 4.0 | 384 | 8.4227 | 0.4945 |
| 0.2686 | 5.0 | 480 | 4.3190 | 0.5473 |
| 0.2987 | 6.0 | 576 | 5.0817 | 0.5164 |
| 0.3415 | 7.0 | 672 | 5.2399 | 0.5127 |
| 0.2396 | 8.0 | 768 | 6.7857 | 0.5018 |
| 0.2618 | 9.0 | 864 | 6.5777 | 0.5055 |
| 0.297 | 10.0 | 960 | 6.6086 | 0.5036 |
| 0.2413 | 11.0 | 1056 | 3.6891 | 0.5236 |
| 0.2074 | 12.0 | 1152 | 6.8991 | 0.5 |
| 0.2029 | 13.0 | 1248 | 5.8597 | 0.5018 |
| 0.2353 | 14.0 | 1344 | 7.3848 | 0.5036 |
| 0.1748 | 15.0 | 1440 | 4.9503 | 0.5109 |
| 0.1885 | 16.0 | 1536 | 7.2151 | 0.4982 |
| 0.1967 | 17.0 | 1632 | 7.9847 | 0.4982 |
| 0.1881 | 18.0 | 1728 | 4.5008 | 0.5109 |
| 0.172 | 19.0 | 1824 | 4.7565 | 0.5273 |
| 0.2222 | 20.0 | 1920 | 6.2814 | 0.4964 |
| 0.1673 | 21.0 | 2016 | 8.1814 | 0.4964 |
| 0.1831 | 22.0 | 2112 | 4.4184 | 0.5164 |
| 0.1121 | 23.0 | 2208 | 6.0737 | 0.4982 |
| 0.1464 | 24.0 | 2304 | 5.3006 | 0.5018 |
| 0.1343 | 25.0 | 2400 | 5.6166 | 0.5036 |
| 0.1385 | 26.0 | 2496 | 6.1437 | 0.5018 |
| 0.1153 | 27.0 | 2592 | 6.3232 | 0.5018 |
| 0.1175 | 28.0 | 2688 | 6.2047 | 0.5036 |
| 0.1107 | 29.0 | 2784 | 7.5461 | 0.4982 |
| 0.0914 | 30.0 | 2880 | 7.4573 | 0.4982 |
| 0.1123 | 31.0 | 2976 | 6.2770 | 0.4982 |
| 0.1268 | 32.0 | 3072 | 5.1979 | 0.5073 |
| 0.1074 | 33.0 | 3168 | 4.9253 | 0.5036 |
| 0.0712 | 34.0 | 3264 | 5.0555 | 0.5018 |
| 0.0792 | 35.0 | 3360 | 6.1480 | 0.4982 |
| 0.1097 | 36.0 | 3456 | 6.5916 | 0.4982 |
| 0.1035 | 37.0 | 3552 | 7.4887 | 0.4982 |
| 0.1066 | 38.0 | 3648 | 6.1041 | 0.5 |
| 0.0887 | 39.0 | 3744 | 6.7739 | 0.4982 |
| 0.0889 | 40.0 | 3840 | 5.5780 | 0.5018 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Image Classification
- Library
- transformers
- Type
- swiftformer
- Created
- Dec 9, 2024
- Updated
- Dec 9, 2024