metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
model-index:
- name: ryan_model314
results: []
ryan_model314
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: 0.2404
- Na Accuracy: 0.96
- Ordinal Accuracy: 0.5921
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 |
---|---|---|---|---|---|
0.3682 | 0.32 | 100 | 0.3209 | 0.942 | 0.5268 |
0.2877 | 0.64 | 200 | 0.2783 | 0.944 | 0.5921 |
0.3079 | 0.96 | 300 | 0.2544 | 0.958 | 0.5338 |
0.1901 | 1.28 | 400 | 0.2632 | 0.948 | 0.6061 |
0.277 | 1.6 | 500 | 0.2404 | 0.96 | 0.5921 |
0.2081 | 1.92 | 600 | 0.2585 | 0.95 | 0.6270 |
0.0809 | 2.24 | 700 | 0.2631 | 0.954 | 0.6737 |
0.1 | 2.56 | 800 | 0.2693 | 0.958 | 0.6364 |
0.0924 | 2.88 | 900 | 0.2566 | 0.962 | 0.6503 |
0.0304 | 3.19 | 1000 | 0.2782 | 0.954 | 0.6527 |
0.0256 | 3.51 | 1100 | 0.2662 | 0.96 | 0.6643 |
0.0424 | 3.83 | 1200 | 0.2670 | 0.962 | 0.6760 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2