Downloads · 30 days
6
5% of all-time downloads
pokemon-vit-fs26
dubattim/pokemon-vit-fs26
pokemon-vit-fs26 is a image classification model from dubattim. 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
126
Public
Parameters
85.8M
2.1 GB on disk
Likes
1
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
- Apr 8, 2026
- Updated
- Apr 8, 2026
- SHA
- b3ea5ab6
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. -->
pokemon-vit-fs26
This model is a fine-tuned version of google/vit-base-patch16-224 on the pokemon (6 classes, custom) dataset. It achieves the following results on the evaluation set:
- Loss: 0.9969
- Accuracy: 0.7895
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: 8
- seed: 42
- optimizer: Use OptimizerNames.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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 10 | 1.5322 | 0.4211 |
| 1.4920 | 2.0 | 20 | 1.3654 | 0.6842 |
| 1.4920 | 3.0 | 30 | 1.2348 | 0.7895 |
| 1.0994 | 4.0 | 40 | 1.1426 | 0.7368 |
| 1.0994 | 5.0 | 50 | 1.0704 | 0.8421 |
| 0.9057 | 6.0 | 60 | 1.0247 | 0.8421 |
| 0.9057 | 7.0 | 70 | 0.9982 | 0.8421 |
| 0.8160 | 8.0 | 80 | 0.9891 | 0.8421 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.2.2
- Datasets 4.8.4
- Tokenizers 0.22.2
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026