convnextv2-femto-1k-224_rice-leaf-disease-augmented-v4_fft
This model is a fine-tuned version of facebook/convnextv2-femto-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2660
- 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 | Accuracy | Validation Loss |
|---|---|---|---|---|
| 2.0082 | 0.5 | 64 | 0.5268 | 1.6771 |
| 1.2603 | 1.0 | 128 | 0.8020 | 0.8211 |
| 0.6327 | 1.5 | 192 | 0.8389 | 0.4743 |
| 0.3835 | 2.0 | 256 | 0.9128 | 0.3028 |
| 0.2059 | 2.5 | 320 | 0.9027 | 0.2902 |
| 0.1242 | 3.0 | 384 | 0.9228 | 0.2034 |
| 0.048 | 3.5 | 448 | 0.9027 | 0.2552 |
| 0.0306 | 4.0 | 512 | 0.9295 | 0.1963 |
| 0.0103 | 4.5 | 576 | 0.9329 | 0.2063 |
| 0.0068 | 5.0 | 640 | 0.9530 | 0.1742 |
| 0.0025 | 5.5 | 704 | 0.9430 | 0.1839 |
| 0.002 | 6.0 | 768 | 0.9463 | 0.1890 |
| 0.0019 | 6.5 | 832 | 0.9228 | 0.3096 |
| 0.0064 | 7.0 | 896 | 0.9262 | 0.2344 |
| 0.0049 | 7.5 | 960 | 0.9228 | 0.2725 |
| 0.003 | 8.0 | 1024 | 0.9463 | 0.2240 |
| 0.0005 | 8.5 | 1088 | 0.9430 | 0.2407 |
| 0.0003 | 9.0 | 1152 | 0.9262 | 0.2760 |
| 0.0002 | 9.5 | 1216 | 0.9463 | 0.2308 |
| 0.0001 | 10.0 | 1280 | 0.9497 | 0.2359 |
| 0.0001 | 10.5 | 1344 | 0.9497 | 0.2367 |
| 0.0001 | 11.0 | 1408 | 0.9497 | 0.2378 |
| 0.0001 | 11.5 | 1472 | 0.9497 | 0.2422 |
| 0.0001 | 12.0 | 1536 | 0.9430 | 0.2403 |
| 0.0001 | 12.5 | 1600 | 0.9463 | 0.2343 |
| 0.0001 | 13.0 | 1664 | 0.9396 | 0.2461 |
| 0.0001 | 13.5 | 1728 | 0.9497 | 0.2434 |
| 0.0001 | 14.0 | 1792 | 0.9430 | 0.2426 |
| 0.0001 | 14.5 | 1856 | 0.9463 | 0.2433 |
| 0.0001 | 15.0 | 1920 | 0.9463 | 0.2432 |
| 0.0001 | 15.5 | 1984 | 0.2458 | 0.9396 |
| 0.0001 | 16.0 | 2048 | 0.2474 | 0.9396 |
| 0.0 | 16.5 | 2112 | 0.2436 | 0.9497 |
| 0.0 | 17.0 | 2176 | 0.2508 | 0.9396 |
| 0.0 | 17.5 | 2240 | 0.2490 | 0.9362 |
| 0.0 | 18.0 | 2304 | 0.2485 | 0.9463 |
| 0.0 | 18.5 | 2368 | 0.2513 | 0.9362 |
| 0.0 | 19.0 | 2432 | 0.2480 | 0.9396 |
| 0.0 | 19.5 | 2496 | 0.2485 | 0.9430 |
| 0.0 | 20.0 | 2560 | 0.2483 | 0.9396 |
| 0.0 | 20.5 | 2624 | 0.2484 | 0.9396 |
| 0.0 | 21.0 | 2688 | 0.2509 | 0.9362 |
| 0.0 | 21.5 | 2752 | 0.2551 | 0.9463 |
| 0.0 | 22.0 | 2816 | 0.2562 | 0.9362 |
| 0.0 | 22.5 | 2880 | 0.2577 | 0.9362 |
| 0.0 | 23.0 | 2944 | 0.2586 | 0.9497 |
| 0.0 | 23.5 | 3008 | 0.2643 | 0.9430 |
| 0.0 | 24.0 | 3072 | 0.2615 | 0.9430 |
| 0.0 | 24.5 | 3136 | 0.2633 | 0.9430 |
| 0.0 | 25.0 | 3200 | 0.2642 | 0.9396 |
| 0.0 | 25.5 | 3264 | 0.2615 | 0.9430 |
| 0.0 | 26.0 | 3328 | 0.2667 | 0.9430 |
| 0.0 | 26.5 | 3392 | 0.2650 | 0.9430 |
| 0.0 | 27.0 | 3456 | 0.2658 | 0.9396 |
| 0.0 | 27.5 | 3520 | 0.2651 | 0.9396 |
| 0.0 | 28.0 | 3584 | 0.2656 | 0.9396 |
| 0.0 | 28.5 | 3648 | 0.2660 | 0.9430 |
| 0.0 | 29.0 | 3712 | 0.2663 | 0.9430 |
| 0.0 | 29.5 | 3776 | 0.2665 | 0.9430 |
| 0.0 | 30.0 | 3840 | 0.2660 | 0.9430 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.1