Boya1_RMSProp_1-e5_10Epoch_swinv2-base-patch4_fold2
This model is a fine-tuned version of microsoft/swinv2-base-patch4-window12-192-22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.2511
- Accuracy: 0.6743
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: 16
- eval_batch_size: 16
- 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 |
---|---|---|---|---|
1.1739 | 1.0 | 923 | 1.1721 | 0.5968 |
1.0295 | 2.0 | 1846 | 1.0306 | 0.6524 |
0.7614 | 3.0 | 2769 | 0.9601 | 0.6719 |
0.7933 | 4.0 | 3692 | 0.9725 | 0.6730 |
0.7602 | 5.0 | 4615 | 1.0029 | 0.6643 |
0.5166 | 6.0 | 5538 | 1.0468 | 0.6759 |
0.3744 | 7.0 | 6461 | 1.1294 | 0.6678 |
0.3112 | 8.0 | 7384 | 1.1635 | 0.6730 |
0.3642 | 9.0 | 8307 | 1.2528 | 0.6765 |
0.3021 | 10.0 | 9230 | 1.2511 | 0.6743 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 10