Boya1_RMSProp_1-e5_10Epoch_swin-base-window7-224-in22k_fold2
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: 1.1859
- Accuracy: 0.67
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 |
---|---|---|---|---|
1.0892 | 1.0 | 923 | 1.2197 | 0.5941 |
0.9178 | 2.0 | 1846 | 1.0433 | 0.6486 |
0.7099 | 3.0 | 2769 | 0.9578 | 0.6786 |
0.7148 | 4.0 | 3692 | 0.9821 | 0.6770 |
0.7006 | 5.0 | 4615 | 1.0065 | 0.6632 |
0.4578 | 6.0 | 5538 | 1.0536 | 0.6673 |
0.421 | 7.0 | 6461 | 1.1039 | 0.6681 |
0.2925 | 8.0 | 7384 | 1.1421 | 0.6654 |
0.2854 | 9.0 | 8307 | 1.1816 | 0.6654 |
0.1695 | 10.0 | 9230 | 1.1859 | 0.67 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 15