vit_itri_downsample_normal_2class
This model is a fine-tuned version of google/vit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.6672
- Accuracy: 0.7880
- Precision: 0.8677
- Recall: 0.7880
- F1: 0.8034
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: 0.0001
- train_batch_size: 24
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2527 | 1.0 | 342 | 1.4323 | 0.6135 | 0.8417 | 0.6135 | 0.6373 |
| 0.1052 | 2.0 | 684 | 1.1099 | 0.6818 | 0.8441 | 0.6818 | 0.7058 |
| 0.0722 | 3.0 | 1026 | 0.7571 | 0.8196 | 0.8691 | 0.8196 | 0.8309 |
| 0.0364 | 4.0 | 1368 | 1.1982 | 0.7126 | 0.8538 | 0.7126 | 0.7347 |
| 0.0211 | 5.0 | 1710 | 1.8288 | 0.6682 | 0.8450 | 0.6682 | 0.6925 |
| 0.0154 | 6.0 | 2052 | 1.7574 | 0.7124 | 0.8537 | 0.7124 | 0.7345 |
| 0.0126 | 7.0 | 2394 | 2.0744 | 0.7140 | 0.8536 | 0.7140 | 0.7360 |
| 0.0027 | 8.0 | 2736 | 1.6455 | 0.7868 | 0.8658 | 0.7868 | 0.8023 |
| 0.0024 | 9.0 | 3078 | 1.8174 | 0.7700 | 0.8630 | 0.7700 | 0.7873 |
| 0.0016 | 10.0 | 3420 | 1.6672 | 0.7880 | 0.8677 | 0.7880 | 0.8034 |
Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1