Boya1_RMSProp_1-e5_10Epoch_swinv2-small-patch4-window16-256_fold2
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: 1.0635
- Accuracy: 0.6730
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 |
---|---|---|---|---|
1.2986 | 1.0 | 1846 | 1.2720 | 0.5857 |
1.0403 | 2.0 | 3692 | 1.0801 | 0.6403 |
1.0869 | 3.0 | 5538 | 1.0102 | 0.6573 |
0.821 | 4.0 | 7384 | 0.9946 | 0.6678 |
1.1018 | 5.0 | 9230 | 1.0078 | 0.6705 |
0.8319 | 6.0 | 11076 | 1.0165 | 0.6732 |
0.811 | 7.0 | 12922 | 1.0611 | 0.6562 |
0.6287 | 8.0 | 14768 | 1.0621 | 0.6735 |
0.562 | 9.0 | 16614 | 1.0481 | 0.6735 |
0.483 | 10.0 | 18460 | 1.0635 | 0.6730 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.1.0
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 10