---
license: mit
base_model: shi-labs/nat-small-in1k-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: msi
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: validation
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6625388813897529
---

<!-- 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. -->

# msi

This model is a fine-tuned version of [shi-labs/nat-small-in1k-224](https://huggingface.co/shi-labs/nat-small-in1k-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6797
- Accuracy: 0.6625

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.4035        | 1.0   | 1858  | 0.7665          | 0.6671   |
| 0.2976        | 2.0   | 3717  | 1.0836          | 0.6372   |
| 0.2552        | 3.0   | 5575  | 1.1942          | 0.6377   |
| 0.219         | 4.0   | 7434  | 1.3987          | 0.6419   |
| 0.1863        | 5.0   | 9292  | 1.5862          | 0.6248   |
| 0.1946        | 6.0   | 11151 | 1.4975          | 0.6848   |
| 0.1679        | 7.0   | 13009 | 1.6209          | 0.6518   |
| 0.1531        | 8.0   | 14868 | 1.6400          | 0.6599   |
| 0.15          | 9.0   | 16726 | 1.6733          | 0.6702   |
| 0.1377        | 10.0  | 18580 | 1.6797          | 0.6625   |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0