switch_gate-leaf-disease-convnextv2-base-1k-224

This model is a fine-tuned version of facebook/convnextv2-base-1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.1746
• Accuracy: 0.9355

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: 300
• eval_batch_size: 300
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 1200
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6169	0.98	16	0.4210	0.8285
0.3115	1.97	32	0.2653	0.8949
0.2375	2.95	48	0.2198	0.9117
0.1999	4.0	65	0.2004	0.9234
0.1916	4.98	81	0.1841	0.9290
0.1771	5.97	97	0.1897	0.9238
0.168	6.95	113	0.1799	0.9308
0.1592	8.0	130	0.1782	0.9332
0.1542	8.98	146	0.1728	0.9322
0.1521	9.97	162	0.1808	0.9346
0.1501	10.95	178	0.1728	0.9388
0.1426	12.0	195	0.1756	0.9346
0.1389	12.98	211	0.1759	0.9369
0.1391	13.97	227	0.1747	0.9364
0.136	14.95	243	0.1744	0.9364
0.1327	15.75	256	0.1746	0.9355

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.1