---
library_name: transformers
base_model: scratch
tags:
- mnist
- handwritten-digits
- image-classification
- pytorch
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: mnist-digit-recognition
  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. -->

# mnist-digit-recognition

This model is a fine-tuned version of [scratch](https://huggingface.co/scratch) on the mnist dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0181
- Accuracy: 0.9943

## 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: 0.0003
- train_batch_size: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0684        | 1.0   | 422  | 0.0517          | 0.9853   |
| 0.0451        | 2.0   | 844  | 0.0343          | 0.9888   |
| 0.039         | 3.0   | 1266 | 0.0289          | 0.9907   |
| 0.0296        | 4.0   | 1688 | 0.0280          | 0.9917   |
| 0.0242        | 5.0   | 2110 | 0.0264          | 0.9918   |


### Framework versions

- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1