metadata
library_name: transformers
license: apache-2.0
base_model: facebook/convnextv2-base-1k-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: convnextv2-base-1k-224_rice-leaf-disease-augmented-v4_fft
results: []
convnextv2-base-1k-224_rice-leaf-disease-augmented-v4_fft
This model is a fine-tuned version of facebook/convnextv2-base-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4315
- Accuracy: 0.9295
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: 32
- eval_batch_size: 32
- 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: 512
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9643 | 0.5 | 128 | 1.7264 | 0.6040 |
| 1.2673 | 1.0 | 256 | 0.7987 | 0.8490 |
| 0.5214 | 1.5 | 384 | 0.3728 | 0.9094 |
| 0.2476 | 2.0 | 512 | 0.4170 | 0.8792 |
| 0.104 | 2.5 | 640 | 0.2676 | 0.9262 |
| 0.0573 | 3.0 | 768 | 0.2642 | 0.9262 |
| 0.0262 | 3.5 | 896 | 0.3739 | 0.9228 |
| 0.0171 | 4.0 | 1024 | 0.3519 | 0.9362 |
| 0.0032 | 4.5 | 1152 | 0.3476 | 0.9295 |
| 0.0011 | 5.0 | 1280 | 0.3547 | 0.9362 |
| 0.0008 | 5.5 | 1408 | 0.3541 | 0.9329 |
| 0.0008 | 6.0 | 1536 | 0.3556 | 0.9329 |
| 0.0008 | 6.5 | 1664 | 0.3524 | 0.9329 |
| 0.0005 | 7.0 | 1792 | 0.3775 | 0.9329 |
| 0.0004 | 7.5 | 1920 | 0.3850 | 0.9329 |
| 0.0003 | 8.0 | 2048 | 0.3900 | 0.9329 |
| 0.0003 | 8.5 | 2176 | 0.3965 | 0.9295 |
| 0.0002 | 9.0 | 2304 | 0.4000 | 0.9295 |
| 0.0002 | 9.5 | 2432 | 0.4019 | 0.9295 |
| 0.0002 | 10.0 | 2560 | 0.4018 | 0.9295 |
| 0.0002 | 10.5 | 2688 | 0.4021 | 0.9295 |
| 0.0002 | 11.0 | 2816 | 0.4063 | 0.9329 |
| 0.0002 | 11.5 | 2944 | 0.4145 | 0.9295 |
| 0.0001 | 12.0 | 3072 | 0.4184 | 0.9295 |
| 0.0001 | 12.5 | 3200 | 0.4249 | 0.9295 |
| 0.0001 | 13.0 | 3328 | 0.4271 | 0.9295 |
| 0.0001 | 13.5 | 3456 | 0.4304 | 0.9295 |
| 0.0001 | 14.0 | 3584 | 0.4315 | 0.9295 |
| 0.0001 | 14.5 | 3712 | 0.4316 | 0.9295 |
| 0.0001 | 15.0 | 3840 | 0.4315 | 0.9295 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0