<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
swin-tiny-patch4-window7-224-finetuned-herbify
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0378
- 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 35
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.94 | 4 | 1.8723 | 0.2787 |
| No log | 1.88 | 8 | 1.5899 | 0.6885 |
| 1.8465 | 2.82 | 12 | 1.1661 | 0.8197 |
| 1.8465 | 4.0 | 17 | 0.5156 | 0.9508 |
| 0.9675 | 4.94 | 21 | 0.2177 | 0.9836 |
| 0.9675 | 5.88 | 25 | 0.0929 | 0.9836 |
| 0.9675 | 6.82 | 29 | 0.0378 | 1.0 |
| 0.2342 | 8.0 | 34 | 0.0128 | 1.0 |
| 0.2342 | 8.94 | 38 | 0.0075 | 1.0 |
| 0.1022 | 9.88 | 42 | 0.0053 | 1.0 |
| 0.1022 | 10.82 | 46 | 0.0049 | 1.0 |
| 0.0553 | 12.0 | 51 | 0.0032 | 1.0 |
| 0.0553 | 12.94 | 55 | 0.0022 | 1.0 |
| 0.0553 | 13.88 | 59 | 0.0017 | 1.0 |
| 0.0278 | 14.82 | 63 | 0.0018 | 1.0 |
| 0.0278 | 16.0 | 68 | 0.0012 | 1.0 |
| 0.0266 | 16.94 | 72 | 0.0011 | 1.0 |
| 0.0266 | 17.88 | 76 | 0.0006 | 1.0 |
| 0.046 | 18.82 | 80 | 0.0007 | 1.0 |
| 0.046 | 20.0 | 85 | 0.0007 | 1.0 |
| 0.046 | 20.94 | 89 | 0.0012 | 1.0 |
| 0.0245 | 21.88 | 93 | 0.0015 | 1.0 |
| 0.0245 | 22.82 | 97 | 0.0011 | 1.0 |
| 0.0249 | 24.0 | 102 | 0.0007 | 1.0 |
| 0.0249 | 24.94 | 106 | 0.0006 | 1.0 |
| 0.0201 | 25.88 | 110 | 0.0005 | 1.0 |
| 0.0201 | 26.82 | 114 | 0.0005 | 1.0 |
| 0.0201 | 28.0 | 119 | 0.0004 | 1.0 |
| 0.0208 | 28.94 | 123 | 0.0004 | 1.0 |
| 0.0208 | 29.88 | 127 | 0.0004 | 1.0 |
| 0.0122 | 30.82 | 131 | 0.0004 | 1.0 |
| 0.0122 | 32.0 | 136 | 0.0004 | 1.0 |
| 0.0222 | 32.94 | 140 | 0.0004 | 1.0 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
