metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-Diastar
results: []
vit-base-patch16-224-Diastar
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0730
- Accuracy: 0.9591
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 0.4516 | 0.9939 | 123 | 0.2494 | 0.8957 |
| 0.2492 | 1.9960 | 247 | 0.1599 | 0.9324 |
| 0.2829 | 2.9980 | 371 | 0.1078 | 0.9461 |
| 0.211 | 4.0 | 495 | 0.0833 | 0.9532 |
| 0.2783 | 4.9939 | 618 | 0.0933 | 0.9514 |
| 0.2205 | 5.9960 | 742 | 0.0825 | 0.9520 |
| 0.1809 | 6.9980 | 866 | 0.0768 | 0.9526 |
| 0.1878 | 8.0 | 990 | 0.0786 | 0.9538 |
| 0.2291 | 8.9939 | 1113 | 0.0750 | 0.9549 |
| 0.1736 | 9.9394 | 1230 | 0.0730 | 0.9591 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1