vit-riceleafbd-7november2025v2
This model is a fine-tuned version of google/vit-base-patch16-224 on the rice-diseases-image-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.0941
- Accuracy: 0.9793
- F1 Score: 0.9818
- Recall: 0.9831
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 150
- num_epochs: 100
- label_smoothing_factor: 0.15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score | Recall |
|---|---|---|---|---|---|---|
| 3.2388 | 1.0 | 19 | 3.1369 | 0.2207 | 0.1485 | 0.2041 |
| 3.0146 | 2.0 | 38 | 2.8588 | 0.3310 | 0.2437 | 0.2877 |
| 2.5872 | 3.0 | 57 | 2.5202 | 0.4552 | 0.4004 | 0.4039 |
| 2.1867 | 4.0 | 76 | 2.1757 | 0.6621 | 0.6470 | 0.6264 |
| 1.8151 | 5.0 | 95 | 1.8032 | 0.8138 | 0.8278 | 0.8189 |
| 1.5088 | 6.0 | 114 | 1.5041 | 0.8483 | 0.8664 | 0.8681 |
| 1.2751 | 7.0 | 133 | 1.3375 | 0.8897 | 0.9038 | 0.9093 |
| 1.1891 | 8.0 | 152 | 1.2427 | 0.9310 | 0.9385 | 0.9387 |
| 1.1147 | 9.0 | 171 | 1.2279 | 0.9379 | 0.9447 | 0.9485 |
| 1.0932 | 10.0 | 190 | 1.1802 | 0.9310 | 0.9387 | 0.9412 |
| 1.0565 | 11.0 | 209 | 1.1744 | 0.9379 | 0.9447 | 0.9485 |
| 1.0276 | 12.0 | 228 | 1.1759 | 0.9379 | 0.9447 | 0.9485 |
| 1.0484 | 13.0 | 247 | 1.1875 | 0.9379 | 0.9464 | 0.9536 |
| 1.0223 | 14.0 | 266 | 1.1503 | 0.9586 | 0.9624 | 0.9632 |
| 1.0341 | 15.0 | 285 | 1.1367 | 0.9655 | 0.9699 | 0.9732 |
| 0.9960 | 16.0 | 304 | 1.1431 | 0.9586 | 0.9639 | 0.9683 |
| 1.0004 | 17.0 | 323 | 1.1354 | 0.9586 | 0.9639 | 0.9683 |
| 0.9870 | 18.0 | 342 | 1.1230 | 0.9724 | 0.9758 | 0.9782 |
| 0.9848 | 19.0 | 361 | 1.1146 | 0.9724 | 0.9758 | 0.9782 |
| 0.9705 | 20.0 | 380 | 1.1073 | 0.9724 | 0.9758 | 0.9782 |
| 0.9817 | 21.0 | 399 | 1.1136 | 0.9655 | 0.9699 | 0.9732 |
| 0.9827 | 22.0 | 418 | 1.1386 | 0.9448 | 0.9522 | 0.9585 |
| 0.9770 | 23.0 | 437 | 1.1081 | 0.9655 | 0.9699 | 0.9732 |
| 0.9720 | 24.0 | 456 | 1.0941 | 0.9793 | 0.9818 | 0.9831 |
| 0.9762 | 25.0 | 475 | 1.0859 | 0.9793 | 0.9818 | 0.9831 |
| 0.9693 | 26.0 | 494 | 1.1249 | 0.9517 | 0.9581 | 0.9634 |
| 0.9670 | 27.0 | 513 | 1.0965 | 0.9724 | 0.9758 | 0.9782 |
| 0.9640 | 28.0 | 532 | 1.1014 | 0.9655 | 0.9699 | 0.9732 |
| 0.9712 | 29.0 | 551 | 1.1083 | 0.9655 | 0.9699 | 0.9732 |
| 0.9704 | 30.0 | 570 | 1.1001 | 0.9655 | 0.9699 | 0.9732 |
| 0.9707 | 31.0 | 589 | 1.0955 | 0.9655 | 0.9699 | 0.9732 |
| 0.9662 | 32.0 | 608 | 1.1017 | 0.9586 | 0.9639 | 0.9683 |
| 0.9667 | 33.0 | 627 | 1.1039 | 0.9586 | 0.9639 | 0.9683 |
| 0.9603 | 34.0 | 646 | 1.0957 | 0.9655 | 0.9699 | 0.9732 |
| 0.9680 | 35.0 | 665 | 1.0971 | 0.9655 | 0.9699 | 0.9732 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2