metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: pizza-or-not-pizza-model
results: []
pizza-or-not-pizza-model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5205
- Accuracy: 0.8403
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: 0.0005
- 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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.9657 | 0.97 | 16 | 1.0966 | 0.6312 |
0.5619 | 2.0 | 33 | 0.7753 | 0.7376 |
0.4391 | 2.97 | 49 | 0.6646 | 0.7947 |
0.2506 | 4.0 | 66 | 0.5963 | 0.8099 |
0.2026 | 4.97 | 82 | 0.5593 | 0.8213 |
0.156 | 5.82 | 96 | 0.5205 | 0.8403 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2