Boya1_RMSProp_1-e5_10Epoch_swin-base-window7-224-in22k_fold5
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.1691
- Accuracy: 0.6763
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 |
---|---|---|---|---|
1.2122 | 1.0 | 924 | 1.1443 | 0.6026 |
1.021 | 2.0 | 1848 | 1.0132 | 0.6476 |
0.7957 | 3.0 | 2772 | 0.9693 | 0.6720 |
0.5847 | 4.0 | 3696 | 0.9842 | 0.6734 |
0.558 | 5.0 | 4620 | 1.0128 | 0.6728 |
0.5896 | 6.0 | 5544 | 1.0401 | 0.6761 |
0.4831 | 7.0 | 6468 | 1.0887 | 0.6736 |
0.2873 | 8.0 | 7392 | 1.1188 | 0.6750 |
0.2429 | 9.0 | 8316 | 1.1565 | 0.6717 |
0.2267 | 10.0 | 9240 | 1.1691 | 0.6763 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 15