vit-base-patch16-224-newly-trained
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1996
- Accuracy: 0.964
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2183 | 0.14 | 10 | 1.6296 | 0.629 |
| 1.4213 | 0.28 | 20 | 0.8637 | 0.899 |
| 0.86 | 0.43 | 30 | 0.4598 | 0.949 |
| 0.614 | 0.57 | 40 | 0.2998 | 0.96 |
| 0.48 | 0.71 | 50 | 0.2337 | 0.967 |
| 0.4123 | 0.85 | 60 | 0.2091 | 0.964 |
| 0.4511 | 0.99 | 70 | 0.1996 | 0.964 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.1
- Datasets 2.14.6
- Tokenizers 0.14.1