Boya1_RMSProp_1-e5_10Epoch_swinv2-small-patch4-window16-256_fold3
This model is a fine-tuned version of microsoft/swinv2-small-patch4-window16-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0546
- Accuracy: 0.6727
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.2323 | 1.0 | 1846 | 1.2173 | 0.5832 |
1.0571 | 2.0 | 3692 | 1.0334 | 0.6419 |
1.0395 | 3.0 | 5538 | 1.0117 | 0.6549 |
0.6959 | 4.0 | 7384 | 0.9770 | 0.6668 |
0.6186 | 5.0 | 9230 | 0.9883 | 0.6708 |
0.4997 | 6.0 | 11076 | 0.9880 | 0.6724 |
0.5568 | 7.0 | 12922 | 1.0422 | 0.6670 |
0.5048 | 8.0 | 14768 | 1.0526 | 0.6730 |
0.5426 | 9.0 | 16614 | 1.0504 | 0.6735 |
0.3886 | 10.0 | 18460 | 1.0546 | 0.6727 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.1.0
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 10