---
library_name: transformers
license: apache-2.0
base_model: Visual-Attention-Network/van-tiny
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: SPIE_MULTICLASS_CHINA_2_0
  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. -->

# SPIE_MULTICLASS_CHINA_2_0

This model is a fine-tuned version of [Visual-Attention-Network/van-tiny](https://huggingface.co/Visual-Attention-Network/van-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3441
- Accuracy: 0.8901

## 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: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 1.7165        | 0.96   | 18   | 1.0539          | 0.7504   |
| 0.842         | 1.9733 | 37   | 0.5513          | 0.8507   |
| 0.4818        | 2.9867 | 56   | 0.4022          | 0.8832   |
| 0.3813        | 4.0    | 75   | 0.3546          | 0.8911   |
| 0.3359        | 4.8    | 90   | 0.3441          | 0.8901   |


### Framework versions

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