Karma_3Class_RMSprop_1e4_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: 0.6636
- Accuracy: 0.7145
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 |
---|---|---|---|---|
0.8273 | 1.0 | 2468 | 0.9004 | 0.6351 |
0.7414 | 2.0 | 4936 | 0.7419 | 0.6871 |
0.7552 | 3.0 | 7404 | 0.7070 | 0.6918 |
0.5357 | 4.0 | 9872 | 0.6848 | 0.7067 |
0.6387 | 5.0 | 12340 | 0.6636 | 0.7145 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 0