Full notebook :
https://github.com/MustafaAlahmid/hugging_face_models/blob/main/Vit-classifier_food_dataset.ipynb
license: apache-2.0 tags:
- generated_from_trainer datasets:
- food101 metrics:
- accuracy model-index:
- name: my_awesome_food_model
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: food101
type: food101
config: default
split: train[:1000]
args: default
metrics:
- name: Accuracy type: accuracy value: 0.985
- task:
name: Image Classification
type: image-classification
dataset:
name: food101
type: food101
config: default
split: train[:1000]
args: default
metrics:
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
my_awesome_food_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2335
- Accuracy: 0.985
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.0523 | 1.0 | 50 | 1.9226 | 0.935 |
1.3718 | 2.0 | 100 | 1.3422 | 0.995 |
1.2298 | 3.0 | 150 | 1.2335 | 0.985 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2