---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- medmnist-v2
metrics:
- accuracy
- f1
model-index:
- name: ViT_bloodmnist_std_0
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: medmnist-v2
      type: medmnist-v2
      config: bloodmnist
      split: validation
      args: bloodmnist
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9690149079216603
    - name: F1
      type: f1
      value: 0.9643637830046188
---

<!-- 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. -->

# ViT_bloodmnist_std_0

This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the medmnist-v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1010
- Accuracy: 0.9690
- F1: 0.9644

## 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | F1     |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|
| 0.3571        | 0.0595 | 200   | 0.1183          | 0.9597   | 0.9577 |
| 0.1349        | 0.1189 | 400   | 0.1324          | 0.9568   | 0.9521 |
| 0.093         | 0.1784 | 600   | 0.1167          | 0.9609   | 0.9587 |
| 0.0777        | 0.2378 | 800   | 0.0855          | 0.9755   | 0.9715 |
| 0.0559        | 0.2973 | 1000  | 0.1004          | 0.9667   | 0.9649 |
| 0.0473        | 0.3567 | 1200  | 0.1123          | 0.9696   | 0.9668 |
| 0.0395        | 0.4162 | 1400  | 0.1074          | 0.9690   | 0.9676 |
| 0.0338        | 0.4756 | 1600  | 0.1189          | 0.9632   | 0.9608 |
| 0.027         | 0.5351 | 1800  | 0.1097          | 0.9772   | 0.9755 |
| 0.0176        | 0.5945 | 2000  | 0.0958          | 0.9784   | 0.9766 |
| 0.0105        | 0.6540 | 2200  | 0.1423          | 0.9720   | 0.9692 |
| 0.0161        | 0.7134 | 2400  | 0.1725          | 0.9650   | 0.9625 |
| 0.0113        | 0.7729 | 2600  | 0.1278          | 0.9708   | 0.9675 |
| 0.0077        | 0.8323 | 2800  | 0.1132          | 0.9766   | 0.9743 |
| 0.0078        | 0.8918 | 3000  | 0.1646          | 0.9690   | 0.9679 |
| 0.007         | 0.9512 | 3200  | 0.1128          | 0.9737   | 0.9718 |
| 0.0036        | 1.0107 | 3400  | 0.1489          | 0.9725   | 0.9735 |
| 0.0047        | 1.0702 | 3600  | 0.1232          | 0.9796   | 0.9787 |
| 0.0158        | 1.1296 | 3800  | 0.1597          | 0.9673   | 0.9615 |
| 0.0082        | 1.1891 | 4000  | 0.1633          | 0.9731   | 0.9731 |
| 0.0029        | 1.2485 | 4200  | 0.1312          | 0.9784   | 0.9770 |
| 0.0029        | 1.3080 | 4400  | 0.1311          | 0.9778   | 0.9760 |
| 0.0005        | 1.3674 | 4600  | 0.1121          | 0.9825   | 0.9818 |
| 0.0039        | 1.4269 | 4800  | 0.2170          | 0.9626   | 0.9587 |
| 0.0097        | 1.4863 | 5000  | 0.1750          | 0.9690   | 0.9693 |
| 0.0065        | 1.5458 | 5200  | 0.1327          | 0.9778   | 0.9768 |
| 0.0047        | 1.6052 | 5400  | 0.1401          | 0.9761   | 0.9744 |
| 0.0035        | 1.6647 | 5600  | 0.1273          | 0.9801   | 0.9803 |
| 0.0001        | 1.7241 | 5800  | 0.1269          | 0.9784   | 0.9777 |
| 0.0           | 1.7836 | 6000  | 0.1601          | 0.9737   | 0.9723 |
| 0.0           | 1.8430 | 6200  | 0.1328          | 0.9772   | 0.9765 |
| 0.0           | 1.9025 | 6400  | 0.1326          | 0.9772   | 0.9765 |
| 0.0           | 1.9620 | 6600  | 0.1333          | 0.9772   | 0.9765 |
| 0.0022        | 2.0214 | 6800  | 0.1839          | 0.9755   | 0.9749 |
| 0.0008        | 2.0809 | 7000  | 0.1914          | 0.9702   | 0.9683 |
| 0.0008        | 2.1403 | 7200  | 0.1954          | 0.9731   | 0.9725 |
| 0.0008        | 2.1998 | 7400  | 0.1592          | 0.9743   | 0.9737 |
| 0.0           | 2.2592 | 7600  | 0.1653          | 0.9755   | 0.9750 |
| 0.0           | 2.3187 | 7800  | 0.1649          | 0.9749   | 0.9747 |
| 0.0           | 2.3781 | 8000  | 0.1654          | 0.9755   | 0.9756 |
| 0.0           | 2.4376 | 8200  | 0.1646          | 0.9755   | 0.9756 |
| 0.0           | 2.4970 | 8400  | 0.1643          | 0.9755   | 0.9756 |
| 0.0           | 2.5565 | 8600  | 0.1713          | 0.9749   | 0.9747 |
| 0.0           | 2.6159 | 8800  | 0.1698          | 0.9755   | 0.9756 |
| 0.0           | 2.6754 | 9000  | 0.1698          | 0.9755   | 0.9756 |
| 0.0           | 2.7348 | 9200  | 0.1696          | 0.9755   | 0.9756 |
| 0.0           | 2.7943 | 9400  | 0.1696          | 0.9755   | 0.9756 |
| 0.0           | 2.8537 | 9600  | 0.1696          | 0.9755   | 0.9756 |
| 0.0           | 2.9132 | 9800  | 0.1697          | 0.9755   | 0.9756 |
| 0.0           | 2.9727 | 10000 | 0.1698          | 0.9755   | 0.9756 |


### Framework versions

- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0