Downloads · 30 days
17
6% of all-time downloads
msi-dinat-mini
aaa12963337/msi-dinat-mini
msi-dinat-mini is a image classification model from aaa12963337. 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
287
Public
Parameters
19.5M
779 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors77.9 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- Model type
- dinat
- Access
- Public
- Created
- Dec 16, 2023
- Updated
- Dec 16, 2023
- SHA
- ecb685ae
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. -->
msi-dinat-mini
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8735
- Accuracy: 0.6308
- F1: 0.4532
- Precision: 0.6338
- Recall: 0.3526
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5414 | 1.0 | 2015 | 0.7584 | 0.5874 | 0.3960 | 0.5427 | 0.3117 |
| 0.4715 | 2.0 | 4031 | 0.7695 | 0.6208 | 0.4593 | 0.6021 | 0.3712 |
| 0.4159 | 3.0 | 6047 | 0.7922 | 0.6230 | 0.4637 | 0.6056 | 0.3757 |
| 0.3774 | 4.0 | 8063 | 0.8166 | 0.6286 | 0.4589 | 0.6235 | 0.3630 |
| 0.3635 | 5.0 | 10078 | 0.8123 | 0.6349 | 0.4889 | 0.6225 | 0.4026 |
| 0.3471 | 6.0 | 12094 | 0.8481 | 0.6265 | 0.4575 | 0.6186 | 0.3630 |
| 0.3616 | 7.0 | 14110 | 0.8605 | 0.6284 | 0.4514 | 0.6279 | 0.3524 |
| 0.3517 | 8.0 | 16126 | 0.8661 | 0.6329 | 0.4600 | 0.6356 | 0.3604 |
| 0.3476 | 9.0 | 18141 | 0.8631 | 0.6330 | 0.4619 | 0.6346 | 0.3631 |
| 0.3469 | 10.0 | 20150 | 0.8735 | 0.6308 | 0.4532 | 0.6338 | 0.3526 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Image Classification
- Library
- transformers
- Type
- dinat
- Created
- Dec 16, 2023
- Updated
- Dec 16, 2023