Boya1_RMSProp_1-e5_10Epoch_swinv2-base-patch4_fold5
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: 1.2529
- Accuracy: 0.6758
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 |
---|---|---|---|---|
1.1907 | 1.0 | 924 | 1.1805 | 0.6048 |
1.0225 | 2.0 | 1848 | 0.9957 | 0.6503 |
0.8132 | 3.0 | 2772 | 0.9354 | 0.6774 |
0.5715 | 4.0 | 3696 | 1.0093 | 0.6725 |
0.6964 | 5.0 | 4620 | 0.9993 | 0.6820 |
0.6956 | 6.0 | 5544 | 1.0237 | 0.6809 |
0.4499 | 7.0 | 6468 | 1.0986 | 0.6807 |
0.4383 | 8.0 | 7392 | 1.2146 | 0.6736 |
0.278 | 9.0 | 8316 | 1.2342 | 0.6753 |
0.2251 | 10.0 | 9240 | 1.2529 | 0.6758 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 19