Boya1_Adamax_1-e4_20Epoch_Deit-small-patch16_fold1
This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 3.6631
- Accuracy: 0.6047
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: 0.0001
- 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: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.2053 | 1.0 | 924 | 1.3479 | 0.5436 |
1.0533 | 2.0 | 1848 | 1.2465 | 0.5745 |
0.9598 | 3.0 | 2772 | 1.2623 | 0.5786 |
0.5046 | 4.0 | 3696 | 1.2915 | 0.5987 |
0.3319 | 5.0 | 4620 | 1.4822 | 0.5906 |
0.2366 | 6.0 | 5544 | 1.7116 | 0.5854 |
0.0946 | 7.0 | 6468 | 2.0587 | 0.5873 |
0.0513 | 8.0 | 7392 | 2.3576 | 0.5971 |
0.0119 | 9.0 | 8316 | 2.5882 | 0.5916 |
0.005 | 10.0 | 9240 | 2.8824 | 0.5900 |
0.0005 | 11.0 | 10164 | 2.9269 | 0.6036 |
0.0002 | 12.0 | 11088 | 3.1123 | 0.5979 |
0.002 | 13.0 | 12012 | 3.1469 | 0.5965 |
0.0001 | 14.0 | 12936 | 3.1949 | 0.6009 |
0.0001 | 15.0 | 13860 | 3.2471 | 0.6033 |
0.0 | 16.0 | 14784 | 3.3448 | 0.6036 |
0.0 | 17.0 | 15708 | 3.4378 | 0.6047 |
0.0 | 18.0 | 16632 | 3.5318 | 0.6047 |
0.0 | 19.0 | 17556 | 3.6207 | 0.6041 |
0.0 | 20.0 | 18480 | 3.6631 | 0.6047 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.1.0
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 0