metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: finetuned-food
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9281675392670157
finetuned-food
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2816
- Accuracy: 0.9282
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: 15
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8456 | 0.39 | 500 | 0.8593 | 0.7634 |
| 0.7824 | 0.78 | 1000 | 0.6625 | 0.8172 |
| 0.4806 | 1.18 | 1500 | 0.4951 | 0.8618 |
| 0.6206 | 1.57 | 2000 | 0.4434 | 0.88 |
| 0.5096 | 1.96 | 2500 | 0.4937 | 0.8683 |
| 0.4576 | 2.35 | 3000 | 0.4060 | 0.8907 |
| 0.3284 | 2.75 | 3500 | 0.3414 | 0.9081 |
| 0.2022 | 3.14 | 4000 | 0.3330 | 0.9118 |
| 0.1332 | 3.53 | 4500 | 0.3043 | 0.9208 |
| 0.1821 | 3.92 | 5000 | 0.2816 | 0.9282 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.2.0.post100
- Datasets 2.12.0
- Tokenizers 0.13.2