Boya2_RMSProp_1-e5_10Epoch_Beit-large-patch16_fold2
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: 2.1871
- Accuracy: 0.7031
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 |
---|---|---|---|---|
1.1303 | 1.0 | 913 | 1.0191 | 0.6482 |
0.6303 | 2.0 | 1826 | 0.9254 | 0.6848 |
0.3776 | 3.0 | 2739 | 1.0216 | 0.6897 |
0.2496 | 4.0 | 3652 | 1.1684 | 0.7028 |
0.1518 | 5.0 | 4565 | 1.3528 | 0.7045 |
0.0696 | 6.0 | 5478 | 1.6928 | 0.6911 |
0.0148 | 7.0 | 6391 | 1.9794 | 0.7006 |
0.0247 | 8.0 | 7304 | 2.1002 | 0.7042 |
0.0007 | 9.0 | 8217 | 2.1914 | 0.7025 |
0.0276 | 10.0 | 9130 | 2.1871 | 0.7031 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 3