Boya1_RMSProp_1-e5_10Epoch_swinv2-base-patch4_fold4
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: 1.3001
- Accuracy: 0.6711
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 |
---|---|---|---|---|
1.1488 | 1.0 | 924 | 1.1016 | 0.6245 |
0.9595 | 2.0 | 1848 | 0.9926 | 0.6535 |
0.766 | 3.0 | 2772 | 0.9713 | 0.6662 |
0.7722 | 4.0 | 3696 | 1.0042 | 0.6743 |
0.6923 | 5.0 | 4620 | 1.0252 | 0.6689 |
0.384 | 6.0 | 5544 | 1.1090 | 0.6646 |
0.4933 | 7.0 | 6468 | 1.1429 | 0.6654 |
0.5012 | 8.0 | 7392 | 1.2321 | 0.6678 |
0.3141 | 9.0 | 8316 | 1.2959 | 0.6695 |
0.3701 | 10.0 | 9240 | 1.3001 | 0.6711 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 19