---
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_1
  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_1

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: 0.3633
- Accuracy: 0.8942

## 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: 1
- 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 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 1.747         | 0.96   | 18   | 1.1983          | 0.7056   |
| 0.9923        | 1.9733 | 37   | 0.6524          | 0.8361   |
| 0.5633        | 2.9867 | 56   | 0.4483          | 0.8729   |
| 0.4208        | 4.0    | 75   | 0.3762          | 0.8911   |
| 0.3879        | 4.8    | 90   | 0.3633          | 0.8942   |


### Framework versions

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