---
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_30
  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: 0.9429991230634317
    - name: F1
      type: f1
      value: 0.9339022055894328
---

<!-- 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_30

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: 0.1697
- Accuracy: 0.9430
- F1: 0.9339

## 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     |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|
| 0.5658        | 0.0595 | 200   | 1.2306          | 0.5076   | 0.4526 |
| 0.2887        | 0.1189 | 400   | 0.6368          | 0.7751   | 0.7410 |
| 0.2406        | 0.1784 | 600   | 0.6641          | 0.7827   | 0.7050 |
| 0.2229        | 0.2378 | 800   | 0.4808          | 0.8072   | 0.7832 |
| 0.1955        | 0.2973 | 1000  | 0.4868          | 0.8002   | 0.7827 |
| 0.1654        | 0.3567 | 1200  | 0.3306          | 0.8657   | 0.8466 |
| 0.1627        | 0.4162 | 1400  | 0.3754          | 0.8732   | 0.8367 |
| 0.1479        | 0.4756 | 1600  | 0.2421          | 0.9118   | 0.8949 |
| 0.1501        | 0.5351 | 1800  | 0.2125          | 0.9235   | 0.9076 |
| 0.1372        | 0.5945 | 2000  | 0.3706          | 0.8616   | 0.8337 |
| 0.1194        | 0.6540 | 2200  | 0.1552          | 0.9451   | 0.9370 |
| 0.1194        | 0.7134 | 2400  | 0.2345          | 0.9194   | 0.8992 |
| 0.1135        | 0.7729 | 2600  | 0.2121          | 0.9287   | 0.9113 |
| 0.1032        | 0.8323 | 2800  | 0.2023          | 0.9299   | 0.9152 |
| 0.1006        | 0.8918 | 3000  | 0.1784          | 0.9451   | 0.9376 |
| 0.0814        | 0.9512 | 3200  | 0.1273          | 0.9533   | 0.9484 |
| 0.0842        | 1.0107 | 3400  | 0.2012          | 0.9363   | 0.9240 |
| 0.0426        | 1.0702 | 3600  | 0.2221          | 0.9340   | 0.9280 |
| 0.06          | 1.1296 | 3800  | 0.2641          | 0.9100   | 0.9037 |
| 0.0632        | 1.1891 | 4000  | 0.1796          | 0.9433   | 0.9339 |
| 0.0506        | 1.2485 | 4200  | 0.2771          | 0.8989   | 0.8838 |
| 0.0467        | 1.3080 | 4400  | 0.1939          | 0.9393   | 0.9265 |
| 0.0469        | 1.3674 | 4600  | 0.1896          | 0.9410   | 0.9322 |
| 0.0457        | 1.4269 | 4800  | 0.1477          | 0.9509   | 0.9479 |
| 0.0416        | 1.4863 | 5000  | 0.2789          | 0.9206   | 0.9086 |
| 0.043         | 1.5458 | 5200  | 0.1832          | 0.9463   | 0.9389 |
| 0.0412        | 1.6052 | 5400  | 0.2100          | 0.9404   | 0.9337 |
| 0.0358        | 1.6647 | 5600  | 0.2368          | 0.9287   | 0.9135 |
| 0.0376        | 1.7241 | 5800  | 0.2668          | 0.9252   | 0.9096 |
| 0.0385        | 1.7836 | 6000  | 0.2145          | 0.9398   | 0.9291 |
| 0.0273        | 1.8430 | 6200  | 0.1995          | 0.9433   | 0.9302 |
| 0.0251        | 1.9025 | 6400  | 0.1900          | 0.9486   | 0.9395 |
| 0.0298        | 1.9620 | 6600  | 0.1617          | 0.9597   | 0.9526 |
| 0.02          | 2.0214 | 6800  | 0.1984          | 0.9463   | 0.9343 |
| 0.0083        | 2.0809 | 7000  | 0.1899          | 0.9498   | 0.9377 |
| 0.0068        | 2.1403 | 7200  | 0.2592          | 0.9340   | 0.9199 |
| 0.0059        | 2.1998 | 7400  | 0.2101          | 0.9428   | 0.9335 |
| 0.0066        | 2.2592 | 7600  | 0.2247          | 0.9422   | 0.9259 |
| 0.0062        | 2.3187 | 7800  | 0.2370          | 0.9439   | 0.9348 |
| 0.0084        | 2.3781 | 8000  | 0.2266          | 0.9474   | 0.9390 |
| 0.0049        | 2.4376 | 8200  | 0.2343          | 0.9480   | 0.9354 |
| 0.0075        | 2.4970 | 8400  | 0.2032          | 0.9486   | 0.9378 |
| 0.0025        | 2.5565 | 8600  | 0.1916          | 0.9515   | 0.9436 |
| 0.0064        | 2.6159 | 8800  | 0.2066          | 0.9533   | 0.9436 |
| 0.004         | 2.6754 | 9000  | 0.2404          | 0.9445   | 0.9321 |
| 0.0029        | 2.7348 | 9200  | 0.2402          | 0.9439   | 0.9322 |
| 0.0008        | 2.7943 | 9400  | 0.2256          | 0.9468   | 0.9365 |
| 0.003         | 2.8537 | 9600  | 0.2265          | 0.9492   | 0.9408 |
| 0.002         | 2.9132 | 9800  | 0.2278          | 0.9515   | 0.9419 |
| 0.0013        | 2.9727 | 10000 | 0.2175          | 0.9504   | 0.9422 |


### Framework versions

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