BaseModel-leaf-disease-convnextv2-base-22k-224-0_1_2_3_4
This model is a fine-tuned version of facebook/convnextv2-base-22k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3419
- Accuracy: 0.8813
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 |
|---|---|---|---|---|
| 1.4178 | 0.98 | 16 | 0.9457 | 0.6215 |
| 0.6112 | 1.97 | 32 | 0.4856 | 0.8294 |
| 0.4468 | 2.95 | 48 | 0.4163 | 0.8575 |
| 0.3659 | 4.0 | 65 | 0.3790 | 0.8715 |
| 0.3481 | 4.98 | 81 | 0.3655 | 0.8785 |
| 0.3338 | 5.97 | 97 | 0.3637 | 0.8748 |
| 0.3216 | 6.95 | 113 | 0.3568 | 0.8752 |
| 0.2948 | 8.0 | 130 | 0.3493 | 0.8808 |
| 0.2944 | 8.98 | 146 | 0.3483 | 0.8808 |
| 0.2857 | 9.97 | 162 | 0.3474 | 0.8808 |
| 0.2711 | 10.95 | 178 | 0.3442 | 0.8790 |
| 0.2682 | 12.0 | 195 | 0.3418 | 0.8813 |
| 0.252 | 12.98 | 211 | 0.3409 | 0.8827 |
| 0.2598 | 13.97 | 227 | 0.3405 | 0.8827 |
| 0.2621 | 14.95 | 243 | 0.3432 | 0.8813 |
| 0.2602 | 15.75 | 256 | 0.3419 | 0.8813 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.1