metadata
library_name: transformers
license: apache-2.0
base_model: facebook/dinov2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: dinov2-base_rice-leaf-disease-augmented-v4_v5_fft
results: []
dinov2-base_rice-leaf-disease-augmented-v4_v5_fft
This model is a fine-tuned version of facebook/dinov2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2683
- Accuracy: 0.9430
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: 64
- eval_batch_size: 64
- seed: 42
- 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: cosine_with_restarts
- lr_scheduler_warmup_steps: 256
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3383 | 0.5 | 64 | 0.4827 | 0.8356 |
| 0.2775 | 1.0 | 128 | 0.3518 | 0.8658 |
| 0.1456 | 1.5 | 192 | 0.5239 | 0.8490 |
| 0.1629 | 2.0 | 256 | 0.2593 | 0.9295 |
| 0.1255 | 2.5 | 320 | 0.3740 | 0.8993 |
| 0.1142 | 3.0 | 384 | 0.3753 | 0.9128 |
| 0.06 | 3.5 | 448 | 0.3722 | 0.9295 |
| 0.0587 | 4.0 | 512 | 0.4174 | 0.9228 |
| 0.0157 | 4.5 | 576 | 0.3364 | 0.9329 |
| 0.0062 | 5.0 | 640 | 0.2237 | 0.9396 |
| 0.0012 | 5.5 | 704 | 0.2186 | 0.9530 |
| 0.0001 | 6.0 | 768 | 0.2342 | 0.9430 |
| 0.0 | 6.5 | 832 | 0.2343 | 0.9430 |
| 0.0 | 7.0 | 896 | 0.2563 | 0.9430 |
| 0.0 | 7.5 | 960 | 0.2597 | 0.9430 |
| 0.0 | 8.0 | 1024 | 0.2546 | 0.9430 |
| 0.0 | 8.5 | 1088 | 0.2553 | 0.9430 |
| 0.0 | 9.0 | 1152 | 0.2562 | 0.9430 |
| 0.0 | 9.5 | 1216 | 0.2570 | 0.9430 |
| 0.0 | 10.0 | 1280 | 0.2564 | 0.9430 |
| 0.0 | 10.5 | 1344 | 0.2566 | 0.9430 |
| 0.0 | 11.0 | 1408 | 0.2565 | 0.9430 |
| 0.0 | 11.5 | 1472 | 0.2578 | 0.9430 |
| 0.0 | 12.0 | 1536 | 0.2580 | 0.9430 |
| 0.0 | 12.5 | 1600 | 0.2571 | 0.9430 |
| 0.0 | 13.0 | 1664 | 0.2590 | 0.9430 |
| 0.0 | 13.5 | 1728 | 0.2599 | 0.9430 |
| 0.0 | 14.0 | 1792 | 0.2595 | 0.9430 |
| 0.0 | 14.5 | 1856 | 0.2594 | 0.9430 |
| 0.0 | 15.0 | 1920 | 0.2597 | 0.9430 |
| 0.0 | 15.5 | 1984 | 0.2596 | 0.9430 |
| 0.0 | 16.0 | 2048 | 0.2597 | 0.9430 |
| 0.0 | 16.5 | 2112 | 0.2605 | 0.9430 |
| 0.0 | 17.0 | 2176 | 0.2602 | 0.9430 |
| 0.0 | 17.5 | 2240 | 0.2608 | 0.9430 |
| 0.0 | 18.0 | 2304 | 0.2617 | 0.9430 |
| 0.0 | 18.5 | 2368 | 0.2628 | 0.9430 |
| 0.0 | 19.0 | 2432 | 0.2621 | 0.9430 |
| 0.0 | 19.5 | 2496 | 0.2621 | 0.9430 |
| 0.0 | 20.0 | 2560 | 0.2621 | 0.9430 |
| 0.0 | 20.5 | 2624 | 0.2621 | 0.9430 |
| 0.0 | 21.0 | 2688 | 0.2625 | 0.9430 |
| 0.0 | 21.5 | 2752 | 0.2625 | 0.9430 |
| 0.0 | 22.0 | 2816 | 0.2638 | 0.9430 |
| 0.0 | 22.5 | 2880 | 0.2648 | 0.9430 |
| 0.0 | 23.0 | 2944 | 0.2648 | 0.9430 |
| 0.0 | 23.5 | 3008 | 0.2645 | 0.9430 |
| 0.0 | 24.0 | 3072 | 0.2652 | 0.9430 |
| 0.0 | 24.5 | 3136 | 0.2654 | 0.9430 |
| 0.0 | 25.0 | 3200 | 0.2654 | 0.9430 |
| 0.0 | 25.5 | 3264 | 0.2654 | 0.9430 |
| 0.0 | 26.0 | 3328 | 0.2658 | 0.9430 |
| 0.0 | 26.5 | 3392 | 0.2657 | 0.9430 |
| 0.0 | 27.0 | 3456 | 0.2670 | 0.9430 |
| 0.0 | 27.5 | 3520 | 0.2680 | 0.9430 |
| 0.0 | 28.0 | 3584 | 0.2681 | 0.9430 |
| 0.0 | 28.5 | 3648 | 0.2687 | 0.9430 |
| 0.0 | 29.0 | 3712 | 0.2684 | 0.9430 |
| 0.0 | 29.5 | 3776 | 0.2683 | 0.9430 |
| 0.0 | 30.0 | 3840 | 0.2683 | 0.9430 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.1