Boya3_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold3
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: 1.7169
- Accuracy: 0.8422
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 |
---|---|---|---|---|
0.4724 | 1.0 | 632 | 0.4432 | 0.8185 |
0.285 | 2.0 | 1264 | 0.5449 | 0.8260 |
0.2677 | 3.0 | 1896 | 0.4843 | 0.8462 |
0.0529 | 4.0 | 2528 | 0.8348 | 0.8339 |
0.0361 | 5.0 | 3160 | 1.0951 | 0.8406 |
0.0006 | 6.0 | 3792 | 1.3311 | 0.8434 |
0.0109 | 7.0 | 4424 | 1.5851 | 0.8304 |
0.0368 | 8.0 | 5056 | 1.6759 | 0.8319 |
0.0 | 9.0 | 5688 | 1.7082 | 0.8406 |
0.0 | 10.0 | 6320 | 1.7169 | 0.8422 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 0