Downloads · 30 days
3
19% of all-time downloads
deit-base-patch16-224-bloodmnist-fold-8
selmamalak/deit-base-patch16-224-bloodmnist-fold-8
deit-base-patch16-224-bloodmnist-fold-8 is a machine learning model from selmamalak. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
16
Public
Repo size
2.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 MB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 21, 2025
- Updated
- Jul 21, 2025
- SHA
- fedd2540
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. -->
deit-base-patch16-224-bloodmnist-fold-8
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the medmnist-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0881
- Accuracy: 0.9710
- Precision: 0.9698
- Recall: 0.9699
- F1: 0.9696
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: 0.005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.5665 | 1.0 | 196 | 0.3301 | 0.8824 | 0.8975 | 0.8670 | 0.8714 |
| 0.4673 | 2.0 | 392 | 0.1627 | 0.9543 | 0.9481 | 0.9526 | 0.9503 |
| 0.3211 | 3.0 | 588 | 0.1627 | 0.9421 | 0.9345 | 0.9362 | 0.9347 |
| 0.3377 | 4.0 | 784 | 0.2708 | 0.9096 | 0.9312 | 0.8939 | 0.9044 |
| 0.3133 | 5.0 | 980 | 0.2002 | 0.9377 | 0.9347 | 0.9398 | 0.9360 |
| 0.2457 | 6.0 | 1176 | 0.1659 | 0.9464 | 0.9426 | 0.9415 | 0.9403 |
| 0.2564 | 7.0 | 1372 | 0.1354 | 0.9570 | 0.9599 | 0.9478 | 0.9520 |
| 0.1807 | 8.0 | 1568 | 0.1057 | 0.9579 | 0.9543 | 0.9559 | 0.9545 |
| 0.1779 | 9.0 | 1764 | 0.0983 | 0.9693 | 0.9680 | 0.9694 | 0.9687 |
| 0.136 | 10.0 | 1960 | 0.0881 | 0.9710 | 0.9698 | 0.9699 | 0.9696 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Library
- peft
- License
- apache-2.0
- Created
- Jul 21, 2025
- Updated
- Jul 21, 2025