Boya2_RMSProp_1-e5_10Epoch_Beit-large-patch16_fold1
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: 2.1531
- Accuracy: 0.7072
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 |
---|---|---|---|---|
0.831 | 1.0 | 914 | 0.9396 | 0.6679 |
0.6588 | 2.0 | 1828 | 0.8923 | 0.7025 |
0.5018 | 3.0 | 2742 | 0.8959 | 0.7146 |
0.3132 | 4.0 | 3656 | 1.1291 | 0.6978 |
0.1473 | 5.0 | 4570 | 1.3243 | 0.7036 |
0.0428 | 6.0 | 5484 | 1.6183 | 0.7011 |
0.0262 | 7.0 | 6398 | 1.9189 | 0.7003 |
0.0221 | 8.0 | 7312 | 2.0468 | 0.7014 |
0.0019 | 9.0 | 8226 | 2.1048 | 0.7118 |
0.0028 | 10.0 | 9140 | 2.1531 | 0.7072 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 3