vit-base-patch16-224-finetuned-noh
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: 0.5148
- Accuracy: 0.8210
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4728 | 1.0 | 23 | 0.4540 | 0.7750 |
| 0.3998 | 2.0 | 46 | 0.4063 | 0.8128 |
| 0.3388 | 3.0 | 69 | 0.3919 | 0.8358 |
| 0.2665 | 4.0 | 92 | 0.4299 | 0.8539 |
| 0.2112 | 5.0 | 115 | 0.4299 | 0.8227 |
| 0.187 | 6.0 | 138 | 0.4721 | 0.8259 |
| 0.1363 | 7.0 | 161 | 0.4639 | 0.8440 |
| 0.119 | 8.0 | 184 | 0.5293 | 0.7898 |
| 0.1042 | 9.0 | 207 | 0.5141 | 0.8161 |
| 0.1153 | 9.5778 | 220 | 0.5148 | 0.8210 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1
- Datasets 2.19.1
- Tokenizers 0.21.0