metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- food101
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-food101-24-12
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: food101
type: food101
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9087524752475248
vit-base-patch16-224-food101-24-12
This model is a fine-tuned version of google/vit-base-patch16-224 on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3328
- Accuracy: 0.9088
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: 5e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1313 | 1.0 | 789 | 0.7486 | 0.8388 |
| 0.735 | 2.0 | 1578 | 0.4546 | 0.8795 |
| 0.7166 | 3.0 | 2367 | 0.3896 | 0.8942 |
| 0.5318 | 4.0 | 3157 | 0.3739 | 0.8961 |
| 0.5326 | 5.0 | 3946 | 0.3576 | 0.9013 |
| 0.4753 | 6.0 | 4735 | 0.3557 | 0.9006 |
| 0.3764 | 7.0 | 5524 | 0.3486 | 0.904 |
| 0.3399 | 8.0 | 6314 | 0.3457 | 0.9046 |
| 0.3987 | 9.0 | 7103 | 0.3378 | 0.9065 |
| 0.2592 | 10.0 | 7892 | 0.3393 | 0.9070 |
| 0.2661 | 11.0 | 8681 | 0.3366 | 0.9080 |
| 0.2632 | 12.0 | 9468 | 0.3328 | 0.9088 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1