vit-base-patch16-224-finetuned-attention-fixation-3-classes
This model is a fine-tuned version of annazhong/vit-base-patch16-224-finetuned-attention-fixation-3-classes on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1739
- Accuracy: 0.4127
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: 150
- eval_batch_size: 150
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 600
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 1 | 1.3475 | 0.4444 |
| No log | 2.0 | 2 | 1.3280 | 0.4127 |
| No log | 3.0 | 3 | 1.1739 | 0.4127 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3