metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-beans
results: []
vit-base-beans
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.0650
- Accuracy: 0.9925
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.2838 | 1.0 | 130 | 0.9624 | 0.2169 |
| 0.1324 | 2.0 | 260 | 0.9699 | 0.1346 |
| 0.143 | 3.0 | 390 | 0.9699 | 0.0998 |
| 0.0833 | 4.0 | 520 | 0.9925 | 0.0650 |
| 0.1099 | 5.0 | 650 | 0.9774 | 0.0824 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1