metadata
license: apache-2.0
base_model: google/vit-large-patch16-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-lage-beans-demo-v5
results: []
vit-lage-beans-demo-v5
This model is a fine-tuned version of google/vit-large-patch16-224 on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.1027
- Accuracy: 0.9792
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7861 | 0.28 | 100 | 0.7609 | 0.725 |
| 0.6276 | 0.56 | 200 | 0.6835 | 0.7764 |
| 0.6089 | 0.83 | 300 | 0.5568 | 0.7931 |
| 0.302 | 1.11 | 400 | 0.5887 | 0.8194 |
| 0.1723 | 1.39 | 500 | 0.2988 | 0.8903 |
| 0.2522 | 1.67 | 600 | 0.2564 | 0.9167 |
| 0.1115 | 1.94 | 700 | 0.1680 | 0.9472 |
| 0.1445 | 2.22 | 800 | 0.2065 | 0.9403 |
| 0.0648 | 2.5 | 900 | 0.1673 | 0.9569 |
| 0.0209 | 2.78 | 1000 | 0.1636 | 0.9569 |
| 0.0003 | 3.06 | 1100 | 0.1293 | 0.9694 |
| 0.0034 | 3.33 | 1200 | 0.0817 | 0.9792 |
| 0.0006 | 3.61 | 1300 | 0.0874 | 0.9833 |
| 0.0023 | 3.89 | 1400 | 0.1076 | 0.9778 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0