|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- medmnist-v2 |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
base_model: facebook/deit-base-patch16-224 |
|
model-index: |
|
- name: blood-deit-base-finetuned |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# blood-deit-base-finetuned |
|
|
|
This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the medmnist-v2 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0767 |
|
- Accuracy: 0.9737 |
|
- Precision: 0.9730 |
|
- Recall: 0.9706 |
|
- F1: 0.9718 |
|
|
|
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.4839 | 1.0 | 187 | 0.2824 | 0.8978 | 0.9057 | 0.8662 | 0.8763 | |
|
| 0.4762 | 2.0 | 374 | 0.2146 | 0.9282 | 0.9246 | 0.9161 | 0.9186 | |
|
| 0.3445 | 3.0 | 561 | 0.2135 | 0.9235 | 0.9244 | 0.9159 | 0.9168 | |
|
| 0.2963 | 4.0 | 748 | 0.1647 | 0.9416 | 0.9323 | 0.9427 | 0.9346 | |
|
| 0.3328 | 5.0 | 935 | 0.1762 | 0.9387 | 0.9323 | 0.9372 | 0.9316 | |
|
| 0.3138 | 6.0 | 1122 | 0.1480 | 0.9439 | 0.9421 | 0.9482 | 0.9426 | |
|
| 0.2489 | 7.0 | 1309 | 0.1134 | 0.9620 | 0.9536 | 0.9609 | 0.9563 | |
|
| 0.193 | 8.0 | 1496 | 0.1020 | 0.9638 | 0.9666 | 0.9581 | 0.9616 | |
|
| 0.1973 | 9.0 | 1683 | 0.0754 | 0.9749 | 0.9733 | 0.9761 | 0.9743 | |
|
| 0.1711 | 10.0 | 1870 | 0.0533 | 0.9819 | 0.9826 | 0.9824 | 0.9825 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
