Boya2_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold5
This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.6377
- Accuracy: 0.8632
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 |
---|---|---|---|---|
0.4668 | 1.0 | 914 | 0.3852 | 0.8385 |
0.2261 | 2.0 | 1828 | 0.3623 | 0.8645 |
0.1143 | 3.0 | 2742 | 0.5165 | 0.8580 |
0.2149 | 4.0 | 3656 | 0.7493 | 0.8626 |
0.1035 | 5.0 | 4570 | 1.0893 | 0.8607 |
0.0224 | 6.0 | 5484 | 1.3211 | 0.8582 |
0.0055 | 7.0 | 6398 | 1.5211 | 0.8604 |
0.0001 | 8.0 | 7312 | 1.6383 | 0.8563 |
0.0001 | 9.0 | 8226 | 1.6304 | 0.8678 |
0.0 | 10.0 | 9140 | 1.6377 | 0.8632 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 1