BaseModel-leaf-disease-convnextv2-base-1k-224-0_1_2_3_4
This model is a fine-tuned version of facebook/convnextv2-base-1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3737
- Accuracy: 0.8738
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: 300
- eval_batch_size: 300
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 1200
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9249 | 0.98 | 16 | 0.6211 | 0.7752 |
| 0.5028 | 1.97 | 32 | 0.4815 | 0.8411 |
| 0.4421 | 2.95 | 48 | 0.4503 | 0.8533 |
| 0.4009 | 4.0 | 65 | 0.4187 | 0.8607 |
| 0.3821 | 4.98 | 81 | 0.4080 | 0.8626 |
| 0.3672 | 5.97 | 97 | 0.3952 | 0.8626 |
| 0.3544 | 6.95 | 113 | 0.3927 | 0.8701 |
| 0.3287 | 8.0 | 130 | 0.3848 | 0.8734 |
| 0.327 | 8.98 | 146 | 0.3877 | 0.8696 |
| 0.3239 | 9.97 | 162 | 0.3783 | 0.8701 |
| 0.3113 | 10.95 | 178 | 0.3746 | 0.8724 |
| 0.3146 | 12.0 | 195 | 0.3736 | 0.8734 |
| 0.3031 | 12.98 | 211 | 0.3747 | 0.8692 |
| 0.3075 | 13.97 | 227 | 0.3752 | 0.8738 |
| 0.3071 | 14.95 | 243 | 0.3759 | 0.8762 |
| 0.3028 | 15.75 | 256 | 0.3737 | 0.8738 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.1