Grietas_10k
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2970
- Accuracy: 0.8787
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: 5e-05
- train_batch_size: 80
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 320
- 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 |
|---|---|---|---|---|
| 0.3932 | 1.0 | 75 | 0.3814 | 0.849 |
| 0.334 | 2.0 | 150 | 0.3357 | 0.8652 |
| 0.3247 | 3.0 | 225 | 0.2965 | 0.8832 |
| 0.3037 | 4.0 | 300 | 0.2992 | 0.8783 |
| 0.2765 | 5.0 | 375 | 0.2970 | 0.8787 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3