metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- 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 an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0014
- Accuracy: 1.0
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0532 | 0.3448 | 100 | 0.0277 | 0.9961 |
| 0.0518 | 0.6897 | 200 | 0.0330 | 0.9942 |
| 0.006 | 1.0345 | 300 | 0.0387 | 0.9923 |
| 0.004 | 1.3793 | 400 | 0.0696 | 0.9845 |
| 0.0032 | 1.7241 | 500 | 0.1609 | 0.9691 |
| 0.0026 | 2.0690 | 600 | 0.0025 | 1.0 |
| 0.0021 | 2.4138 | 700 | 0.0020 | 1.0 |
| 0.0018 | 2.7586 | 800 | 0.0017 | 1.0 |
| 0.0016 | 3.1034 | 900 | 0.0016 | 1.0 |
| 0.0015 | 3.4483 | 1000 | 0.0015 | 1.0 |
| 0.0014 | 3.7931 | 1100 | 0.0014 | 1.0 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1