---
license: mit
base_model: shi-labs/nat-mini-in1k-224
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: msi-mini2
  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. -->

# msi-mini2

This model is a fine-tuned version of [shi-labs/nat-mini-in1k-224](https://huggingface.co/shi-labs/nat-mini-in1k-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- eval_loss: 1.0132
- eval_accuracy: 0.6103
- eval_runtime: 97.1589
- eval_samples_per_second: 294.528
- eval_steps_per_second: 18.413
- epoch: 2.0
- step: 4031

## 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

### Framework versions

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