swin-base-patch4-window7-224_rice-leaf-disease-augmented-v4_tl

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: 0.4669
• Accuracy: 0.8356

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: 0.0003
• 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	Accuracy	Validation Loss
2.0735	0.5	64	0.2886	1.8963
1.7495	1.0	128	0.5805	1.4919
1.3696	1.5	192	0.6846	1.1557
1.1089	2.0	256	0.7383	0.9138
0.9257	2.5	320	0.7483	0.8014
0.8212	3.0	384	0.7752	0.7178
0.7517	3.5	448	0.8020	0.6606
0.706	4.0	512	0.8221	0.6248
0.6772	4.5	576	0.8188	0.6039
0.6558	5.0	640	0.8087	0.6038
0.6427	5.5	704	0.8121	0.6080
0.6385	6.0	768	0.8087	0.5981
0.6549	6.5	832	0.7886	0.6049
0.5978	7.0	896	0.8188	0.5738
0.5935	7.5	960	0.8322	0.5369
0.5571	8.0	1024	0.8423	0.5211
0.5359	8.5	1088	0.8255	0.5201
0.5455	9.0	1152	0.8188	0.5270
0.5198	9.5	1216	0.8322	0.5102
0.5169	10.0	1280	0.8221	0.5094
0.5213	10.5	1344	0.5097	0.8221
0.5069	11.0	1408	0.5042	0.8188
0.5035	11.5	1472	0.5083	0.8289
0.4881	12.0	1536	0.4868	0.8356
0.4768	12.5	1600	0.4753	0.8356
0.4612	13.0	1664	0.4762	0.8322
0.4561	13.5	1728	0.4616	0.8356
0.4476	14.0	1792	0.4690	0.8356
0.448	14.5	1856	0.4665	0.8322
0.4418	15.0	1920	0.4669	0.8356

Framework versions

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