vit-base-patch16-224_rice-leaf-disease-augmented-v4_fft

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

• Loss: 0.2195
• Accuracy: 0.9564

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_ratio: 0.1
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
1.9654	0.5	64	0.5	1.5817
1.1667	1.0	128	0.8255	0.6758
0.4198	1.5	192	0.9027	0.2913
0.1774	2.0	256	0.9597	0.1539
0.038	2.5	320	0.9564	0.1636
0.0248	3.0	384	0.9430	0.1796
0.007	3.5	448	0.9497	0.1965
0.0023	4.0	512	0.9497	0.2117
0.0012	4.5	576	0.9463	0.2007
0.001	5.0	640	0.9564	0.1974
0.0008	5.5	704	0.9564	0.2004
0.0007	6.0	768	0.9564	0.2007
0.0008	6.5	832	0.9564	0.2008
0.0006	7.0	896	0.9597	0.2012
0.0005	7.5	960	0.9597	0.2021
0.0004	8.0	1024	0.9564	0.2069
0.0004	8.5	1088	0.2108	0.9564
0.0003	9.0	1152	0.2105	0.9564
0.0003	9.5	1216	0.2086	0.9564
0.0002	10.0	1280	0.2129	0.9564
0.0002	10.5	1344	0.2139	0.9564
0.0002	11.0	1408	0.2140	0.9564
0.0002	11.5	1472	0.2141	0.9564
0.0002	12.0	1536	0.2170	0.9564
0.0002	12.5	1600	0.2149	0.9564
0.0002	13.0	1664	0.2193	0.9564
0.0001	13.5	1728	0.2187	0.9564
0.0001	14.0	1792	0.2197	0.9564
0.0001	14.5	1856	0.2194	0.9564
0.0001	15.0	1920	0.2195	0.9564

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0