swin-base-patch4-window7-224_rice-leaf-disease-augmented-v4_fft

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3287
• Accuracy: 0.9463

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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.8712	0.5	64	1.3077	0.5872
0.7401	1.0	128	0.3734	0.8591
0.2476	1.5	192	0.2913	0.9128
0.1242	2.0	256	0.2218	0.9362
0.0492	2.5	320	0.2208	0.9430
0.0405	3.0	384	0.2730	0.9463
0.0094	3.5	448	0.2382	0.9362
0.0068	4.0	512	0.2759	0.9430
0.0011	4.5	576	0.3000	0.9530
0.0013	5.0	640	0.2777	0.9430
0.0007	5.5	704	0.2812	0.9530
0.0007	6.0	768	0.2854	0.9530
0.0006	6.5	832	0.2698	0.9564
0.01	7.0	896	0.4170	0.9228
0.0175	7.5	960	0.4012	0.9295
0.0119	8.0	1024	0.3337	0.9463
0.005	8.5	1088	0.5413	0.9228
0.0023	9.0	1152	0.2959	0.9430
0.0005	9.5	1216	0.4358	0.9430
0.0006	10.0	1280	0.3648	0.9430
0.0005	10.5	1344	0.3561	0.9497
0.0001	11.0	1408	0.3526	0.9430
0.0001	11.5	1472	0.3208	0.9497
0.0001	12.0	1536	0.2856	0.9530
0.0006	12.5	1600	0.2808	0.9396
0.0025	13.0	1664	0.3422	0.9463
0.0012	13.5	1728	0.3137	0.9497
0.0003	14.0	1792	0.3206	0.9497
0.0005	14.5	1856	0.3344	0.9463
0.0003	15.0	1920	0.3287	0.9463

Framework versions

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