efficientnet-b0_rice-leaf-disease-augmented-v4_fft
This model is a fine-tuned version of google/efficientnet-b0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3800
- Accuracy: 0.9128
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 | Accuracy | Validation Loss |
|---|---|---|---|---|
| 2.0658 | 0.5 | 64 | 0.2450 | 1.9987 |
| 1.9318 | 1.0 | 128 | 0.4262 | 1.7967 |
| 1.6451 | 1.5 | 192 | 0.5604 | 1.4543 |
| 1.2851 | 2.0 | 256 | 0.6846 | 1.0678 |
| 0.9017 | 2.5 | 320 | 0.7617 | 0.8011 |
| 0.6891 | 3.0 | 384 | 0.8054 | 0.6284 |
| 0.5118 | 3.5 | 448 | 0.8020 | 0.6124 |
| 0.4458 | 4.0 | 512 | 0.8121 | 0.6052 |
| 0.356 | 4.5 | 576 | 0.8289 | 0.5032 |
| 0.3255 | 5.0 | 640 | 0.8523 | 0.4429 |
| 0.294 | 5.5 | 704 | 0.8490 | 0.4829 |
| 0.2856 | 6.0 | 768 | 0.8389 | 0.4863 |
| 0.289 | 6.5 | 832 | 0.8523 | 0.4306 |
| 0.2357 | 7.0 | 896 | 0.8591 | 0.4408 |
| 0.183 | 7.5 | 960 | 0.8691 | 0.3810 |
| 0.1446 | 8.0 | 1024 | 0.8624 | 0.3680 |
| 0.1094 | 8.5 | 1088 | 0.8826 | 0.3557 |
| 0.102 | 9.0 | 1152 | 0.8826 | 0.3555 |
| 0.0752 | 9.5 | 1216 | 0.8826 | 0.3514 |
| 0.0828 | 10.0 | 1280 | 0.8691 | 0.4008 |
| 0.0758 | 10.5 | 1344 | 0.8792 | 0.3509 |
| 0.0699 | 11.0 | 1408 | 0.8893 | 0.3737 |
| 0.059 | 11.5 | 1472 | 0.8859 | 0.3488 |
| 0.0504 | 12.0 | 1536 | 0.9027 | 0.3544 |
| 0.0381 | 12.5 | 1600 | 0.8926 | 0.3867 |
| 0.0293 | 13.0 | 1664 | 0.8893 | 0.3593 |
| 0.0257 | 13.5 | 1728 | 0.8993 | 0.3230 |
| 0.0258 | 14.0 | 1792 | 0.8893 | 0.4092 |
| 0.0249 | 14.5 | 1856 | 0.8859 | 0.4291 |
| 0.0187 | 15.0 | 1920 | 0.8993 | 0.3305 |
| 0.0226 | 15.5 | 1984 | 0.3599 | 0.8893 |
| 0.0222 | 16.0 | 2048 | 0.3777 | 0.8993 |
| 0.0151 | 16.5 | 2112 | 0.3345 | 0.9060 |
| 0.0181 | 17.0 | 2176 | 0.3589 | 0.8960 |
| 0.0144 | 17.5 | 2240 | 0.3440 | 0.8960 |
| 0.0117 | 18.0 | 2304 | 0.4319 | 0.9027 |
| 0.013 | 18.5 | 2368 | 0.3972 | 0.8960 |
| 0.0111 | 19.0 | 2432 | 0.3337 | 0.8926 |
| 0.0106 | 19.5 | 2496 | 0.3284 | 0.9027 |
| 0.0114 | 20.0 | 2560 | 0.3483 | 0.9027 |
| 0.0111 | 20.5 | 2624 | 0.3425 | 0.8993 |
| 0.0106 | 21.0 | 2688 | 0.3333 | 0.8993 |
| 0.011 | 21.5 | 2752 | 0.3795 | 0.9027 |
| 0.0106 | 22.0 | 2816 | 0.4228 | 0.9027 |
| 0.0075 | 22.5 | 2880 | 0.4410 | 0.8859 |
| 0.0075 | 23.0 | 2944 | 0.3461 | 0.8993 |
| 0.0057 | 23.5 | 3008 | 0.3992 | 0.9027 |
| 0.0058 | 24.0 | 3072 | 0.3577 | 0.9060 |
| 0.0041 | 24.5 | 3136 | 0.4393 | 0.8993 |
| 0.0042 | 25.0 | 3200 | 0.3816 | 0.8960 |
| 0.0045 | 25.5 | 3264 | 0.4059 | 0.9027 |
| 0.0033 | 26.0 | 3328 | 0.4299 | 0.8960 |
| 0.0038 | 26.5 | 3392 | 0.4605 | 0.8993 |
| 0.004 | 27.0 | 3456 | 0.3973 | 0.9027 |
| 0.0033 | 27.5 | 3520 | 0.4126 | 0.9094 |
| 0.0049 | 28.0 | 3584 | 0.3783 | 0.9128 |
| 0.0027 | 28.5 | 3648 | 0.3632 | 0.9094 |
| 0.0033 | 29.0 | 3712 | 0.4586 | 0.9027 |
| 0.0039 | 29.5 | 3776 | 0.4505 | 0.8960 |
| 0.0037 | 30.0 | 3840 | 0.3800 | 0.9128 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.1