---
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: quickdraw-DeiT-tiny-c
  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. -->

# quickdraw-DeiT-tiny-c

This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9628
- Accuracy: 0.7773

## 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: 0.0008
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10000
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
| 1.315         | 0.5688 | 5000  | 1.2585          | 0.6844   |
| 1.1484        | 1.1377 | 10000 | 1.1506          | 0.7091   |
| 1.0423        | 1.7065 | 15000 | 1.0410          | 0.7327   |
| 0.9596        | 2.2753 | 20000 | 0.9754          | 0.7498   |
| 0.9363        | 2.8441 | 25000 | 0.9489          | 0.7557   |
| 0.8768        | 3.4130 | 30000 | 0.9197          | 0.7633   |
| 0.8655        | 3.9818 | 35000 | 0.8970          | 0.7688   |
| 0.815         | 4.5506 | 40000 | 0.8845          | 0.7724   |
| 0.748         | 5.1195 | 45000 | 0.8729          | 0.7761   |
| 0.7522        | 5.6883 | 50000 | 0.8562          | 0.78     |
| 0.6854        | 6.2571 | 55000 | 0.8654          | 0.7805   |
| 0.6899        | 6.8259 | 60000 | 0.8529          | 0.7838   |
| 0.6162        | 7.3948 | 65000 | 0.8787          | 0.7821   |
| 0.6159        | 7.9636 | 70000 | 0.8742          | 0.7837   |
| 0.5498        | 8.5324 | 75000 | 0.9197          | 0.7801   |
| 0.5087        | 9.1013 | 80000 | 0.9529          | 0.7782   |
| 0.5053        | 9.6701 | 85000 | 0.9628          | 0.7773   |


### Framework versions

- Transformers 4.41.0
- Pytorch 2.2.1
- Datasets 2.19.1
- Tokenizers 0.19.1