metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_food_model
results: []
my_awesome_food_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4788
- Accuracy: 0.918
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2354 | 0.992 | 62 | 1.2067 | 0.913 |
| 0.8106 | 2.0 | 125 | 0.8617 | 0.917 |
| 0.6279 | 2.992 | 187 | 0.6817 | 0.915 |
| 0.5143 | 4.0 | 250 | 0.5720 | 0.92 |
| 0.4102 | 4.992 | 312 | 0.4917 | 0.935 |
| 0.3593 | 6.0 | 375 | 0.4655 | 0.928 |
| 0.3556 | 6.944 | 434 | 0.4788 | 0.918 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1