metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-batch-32
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: vuongnhathien/30VNFoods
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8755952380952381
vit-base-batch-32
This model is a fine-tuned version of google/vit-base-patch16-224 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:
- Loss: 0.6201
- Accuracy: 0.8756
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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6735 | 1.0 | 550 | 0.8003 | 0.7583 |
0.4048 | 2.0 | 1100 | 0.6471 | 0.8266 |
0.2506 | 3.0 | 1650 | 0.6220 | 0.8354 |
0.1521 | 4.0 | 2200 | 0.6406 | 0.8493 |
0.0812 | 5.0 | 2750 | 0.6855 | 0.8545 |
0.0279 | 6.0 | 3300 | 0.6767 | 0.8648 |
0.0094 | 7.0 | 3850 | 0.6252 | 0.8744 |
0.0074 | 8.0 | 4400 | 0.6064 | 0.8751 |
0.0056 | 9.0 | 4950 | 0.5997 | 0.8783 |
0.0016 | 10.0 | 5500 | 0.6009 | 0.8767 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2