Boya1_RMSProp_1-e5_10Epoch_swinv2-large-patch4_fold2
This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.9422
- Accuracy: 0.6681
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: 8
- eval_batch_size: 8
- 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 |
---|---|---|---|---|
1.2406 | 1.0 | 1846 | 1.0458 | 0.6359 |
0.9629 | 2.0 | 3692 | 0.9494 | 0.6608 |
0.9327 | 3.0 | 5538 | 0.9770 | 0.6662 |
0.6166 | 4.0 | 7384 | 0.9930 | 0.6749 |
0.5934 | 5.0 | 9230 | 1.1939 | 0.6749 |
0.4129 | 6.0 | 11076 | 1.3358 | 0.6735 |
0.404 | 7.0 | 12922 | 1.5652 | 0.6716 |
0.304 | 8.0 | 14768 | 1.7273 | 0.6673 |
0.227 | 9.0 | 16614 | 1.9285 | 0.6619 |
0.2788 | 10.0 | 18460 | 1.9422 | 0.6681 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 10