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-add-2-decay
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: 0.8867063492063492
vit-base-add-2-decay
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: 0.5253
- Accuracy: 0.8867
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: 64
- 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 |
---|---|---|---|---|
0.6211 | 1.0 | 275 | 0.6582 | 0.7996 |
0.3091 | 2.0 | 550 | 0.5436 | 0.8457 |
0.1674 | 3.0 | 825 | 0.5812 | 0.8565 |
0.0947 | 4.0 | 1100 | 0.5674 | 0.8648 |
0.0335 | 5.0 | 1375 | 0.6408 | 0.8517 |
0.0235 | 6.0 | 1650 | 0.5589 | 0.8803 |
0.006 | 7.0 | 1925 | 0.5129 | 0.8859 |
0.0054 | 8.0 | 2200 | 0.4975 | 0.8922 |
0.0017 | 9.0 | 2475 | 0.4996 | 0.8926 |
0.0027 | 10.0 | 2750 | 0.4998 | 0.8915 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2