metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
model-index:
- name: ryan_model3272024
results: []
ryan_model3272024
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: 1.0327
- Na Accuracy: 0.956
- Ordinal Accuracy: 0.568
- Ordinal Mae: 56.3484
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 | Na Accuracy | Ordinal Accuracy | Ordinal Mae |
|---|---|---|---|---|---|---|
| 1.3578 | 0.32 | 100 | 1.2058 | 0.944 | 0.54 | 90.9846 |
| 1.089 | 0.64 | 200 | 1.0987 | 0.95 | 0.548 | 120.7097 |
| 0.924 | 0.96 | 300 | 1.0838 | 0.946 | 0.568 | 76.7982 |
| 0.694 | 1.28 | 400 | 1.0680 | 0.942 | 0.556 | 105.6312 |
| 0.7739 | 1.6 | 500 | 1.0327 | 0.956 | 0.568 | 56.3484 |
| 0.5935 | 1.92 | 600 | 1.0479 | 0.932 | 0.598 | 50.4520 |
| 0.3525 | 2.24 | 700 | 1.1915 | 0.94 | 0.578 | 68.5099 |
| 0.2385 | 2.56 | 800 | 1.1303 | 0.948 | 0.586 | 43.0221 |
| 0.3423 | 2.88 | 900 | 1.1767 | 0.94 | 0.604 | 72.1437 |
| 0.0674 | 3.19 | 1000 | 1.2294 | 0.938 | 0.606 | 28.0702 |
| 0.1206 | 3.51 | 1100 | 1.2336 | 0.938 | 0.616 | 65.0794 |
| 0.1261 | 3.83 | 1200 | 1.2907 | 0.938 | 0.604 | 45.8334 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2