vit-base-patch16-224-finetuned-for-agricultural
This model is a fine-tuned version of xiaopch/vit-base-patch16-224-finetuned on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9246
- Accuracy: 0.7309
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9131 | 1.0 | 35 | 1.0878 | 0.6847 |
| 0.8066 | 2.0 | 70 | 0.9933 | 0.7189 |
| 0.7259 | 3.0 | 105 | 0.9445 | 0.7249 |
| 0.6719 | 4.0 | 140 | 0.9246 | 0.7309 |
| 0.6056 | 5.0 | 175 | 0.9258 | 0.7229 |
| 0.5576 | 6.0 | 210 | 0.9230 | 0.7309 |
| 0.5113 | 7.0 | 245 | 0.9152 | 0.7169 |
| 0.488 | 8.0 | 280 | 0.9119 | 0.7209 |
| 0.4822 | 9.0 | 315 | 0.9061 | 0.7269 |
| 0.4163 | 10.0 | 350 | 0.9039 | 0.7289 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0