metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-food-items-v1
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: beans
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9236363636363636
vit-base-food-items-v1
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.3363
- Accuracy: 0.9236
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4195 | 0.6579 | 100 | 0.5028 | 0.9055 |
| 0.1072 | 1.3158 | 200 | 0.3794 | 0.8945 |
| 0.0326 | 1.9737 | 300 | 0.3832 | 0.9055 |
| 0.0207 | 2.6316 | 400 | 0.3363 | 0.9236 |
| 0.0167 | 3.2895 | 500 | 0.3373 | 0.9236 |
| 0.0153 | 3.9474 | 600 | 0.3374 | 0.9236 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1