|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google/vit-base-patch16-224-in21k |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- cifar-10 |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: vit-base-patch16-224-in21k-finetuned-cifar10 |
|
|
results: |
|
|
- task: |
|
|
name: Image Classification |
|
|
type: image-classification |
|
|
dataset: |
|
|
name: cifar-10 |
|
|
type: cifar-10 |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.9877 |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# vit-base-patch16-224-in21k-finetuned-cifar10 |
|
|
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the cifar-10 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1126 |
|
|
- Accuracy: 0.9877 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
```Python |
|
|
from transformers import pipeline |
|
|
|
|
|
pipe = pipeline("image-classification", "avanishd/vit-base-patch16-224-in21k-finetuned-cifar10") |
|
|
pipe(image) |
|
|
``` |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
More information needed |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 5e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 128 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 3 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| 0.4166 | 1.0 | 313 | 0.2324 | 0.9791 | |
|
|
| 0.3247 | 2.0 | 626 | 0.1320 | 0.9875 | |
|
|
| 0.2661 | 2.992 | 936 | 0.1126 | 0.9877 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.5.0 |
|
|
- Tokenizers 0.21.1 |
|
|
|
