switch_gate-leaf-disease-convnextv2-base-22k-224

This model is a fine-tuned version of facebook/convnextv2-base-22k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.1674
• Accuracy: 0.9379

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
0.6005	0.98	16	0.3258	0.8701
0.234	1.97	32	0.2121	0.9173
0.197	2.95	48	0.1869	0.9271
0.1613	4.0	65	0.1692	0.9336
0.1536	4.98	81	0.1616	0.9397
0.1426	5.97	97	0.1628	0.9355
0.132	6.95	113	0.1609	0.9407
0.1304	8.0	130	0.1597	0.9402
0.1245	8.98	146	0.1628	0.9350
0.1224	9.97	162	0.1664	0.9364
0.1143	10.95	178	0.1615	0.9388
0.1106	12.0	195	0.1641	0.9393
0.103	12.98	211	0.1689	0.9374
0.1047	13.97	227	0.1673	0.9379
0.102	14.95	243	0.1681	0.9397
0.1038	15.75	256	0.1674	0.9379

Framework versions

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