deit-base-patch16-224_rice-leaf-disease-augmented_fft_012825

This model is a fine-tuned version of facebook/deit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0330
• Accuracy: 0.9915

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: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
1.5925	1.0	250	0.7635	0.7925
0.4178	2.0	500	0.9385	0.2078
0.0954	3.0	750	0.9785	0.0678
0.0159	4.0	1000	0.9795	0.0617
0.0032	5.0	1250	0.9905	0.0254
0.0012	6.0	1500	0.9915	0.0223
0.0012	7.0	1750	0.9925	0.0209
0.0009	8.0	2000	0.992	0.0201
0.0004	9.0	2250	0.9935	0.0185
0.0091	10.0	2500	0.986	0.0532
0.0012	11.0	2750	0.99	0.0314
0.0007	12.0	3000	0.9935	0.0278
0.0004	13.0	3250	0.9855	0.0561
0.0003	14.0	3500	0.987	0.0391
0.0006	15.0	3750	0.9915	0.0330

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0