Boya1_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold4
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: 1.2276
- Accuracy: 0.8407
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.3425 | 1.0 | 923 | 0.4401 | 0.8230 |
0.2611 | 2.0 | 1846 | 0.4241 | 0.8314 |
0.1595 | 3.0 | 2769 | 0.5720 | 0.8363 |
0.1001 | 4.0 | 3692 | 0.9325 | 0.8344 |
0.0096 | 5.0 | 4615 | 1.2276 | 0.8407 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 0