---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: model
  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. -->

# model

This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co./google/vit-base-patch16-224-in21k) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1898
- Accuracy: 0.9243

## 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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2732        | 0.1   | 100  | 0.3969          | 0.8461   |
| 0.2784        | 0.21  | 200  | 0.3714          | 0.8579   |
| 0.301         | 0.31  | 300  | 0.3504          | 0.8376   |
| 0.2372        | 0.42  | 400  | 0.3391          | 0.8812   |
| 0.3136        | 0.52  | 500  | 0.2559          | 0.8967   |
| 0.3517        | 0.62  | 600  | 0.4141          | 0.8397   |
| 0.3312        | 0.73  | 700  | 0.3043          | 0.8841   |
| 0.2515        | 0.83  | 800  | 0.2541          | 0.9062   |
| 0.2854        | 0.93  | 900  | 0.2561          | 0.9006   |
| 0.2594        | 1.04  | 1000 | 0.2681          | 0.9020   |
| 0.177         | 1.14  | 1100 | 0.3406          | 0.8773   |
| 0.2717        | 1.25  | 1200 | 0.2266          | 0.9171   |
| 0.2197        | 1.35  | 1300 | 0.2080          | 0.9236   |
| 0.155         | 1.45  | 1400 | 0.2048          | 0.9236   |
| 0.2657        | 1.56  | 1500 | 0.2037          | 0.9256   |
| 0.118         | 1.66  | 1600 | 0.2616          | 0.9096   |
| 0.1823        | 1.77  | 1700 | 0.2158          | 0.9241   |
| 0.2175        | 1.87  | 1800 | 0.2159          | 0.9182   |
| 0.143         | 1.97  | 1900 | 0.1898          | 0.9243   |
| 0.1051        | 2.08  | 2000 | 0.2308          | 0.9226   |
| 0.1963        | 2.18  | 2100 | 0.2354          | 0.9205   |
| 0.0524        | 2.28  | 2200 | 0.2298          | 0.9282   |
| 0.097         | 2.39  | 2300 | 0.2495          | 0.9241   |
| 0.0744        | 2.49  | 2400 | 0.2493          | 0.9194   |
| 0.0744        | 2.6   | 2500 | 0.2429          | 0.9323   |
| 0.0345        | 2.7   | 2600 | 0.2587          | 0.9252   |
| 0.0097        | 2.8   | 2700 | 0.2284          | 0.9265   |
| 0.0775        | 2.91  | 2800 | 0.2242          | 0.9321   |
| 0.0634        | 3.01  | 2900 | 0.2314          | 0.9286   |
| 0.0109        | 3.12  | 3000 | 0.2203          | 0.9338   |
| 0.0039        | 3.22  | 3100 | 0.2575          | 0.9358   |
| 0.0139        | 3.32  | 3200 | 0.2570          | 0.9356   |
| 0.0358        | 3.43  | 3300 | 0.2630          | 0.9335   |
| 0.0347        | 3.53  | 3400 | 0.2633          | 0.9358   |
| 0.0408        | 3.63  | 3500 | 0.2591          | 0.9335   |
| 0.041         | 3.74  | 3600 | 0.2613          | 0.9367   |
| 0.004         | 3.84  | 3700 | 0.2587          | 0.9370   |
| 0.0389        | 3.95  | 3800 | 0.2535          | 0.9373   |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1