plant_disease_detection-beans

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

• Loss: 0.0711
• Accuracy: 0.9850

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0983	0.98	16	0.8079	0.7143
0.5524	1.97	32	0.2697	0.9624
0.2699	2.95	48	0.0926	0.9549
0.0991	4.0	65	0.0551	0.9774
0.0722	4.98	81	0.0435	0.9925
0.0584	5.97	97	0.0328	0.9850
0.0451	6.95	113	0.0478	0.9774
0.0321	8.0	130	0.0532	0.9925
0.0298	8.98	146	0.0802	0.9774
0.0516	9.97	162	0.0391	0.9774
0.0396	10.95	178	0.0720	0.9774
0.0358	12.0	195	0.0540	0.9850
0.027	12.98	211	0.0467	0.9774
0.0236	13.97	227	0.0184	0.9925
0.0272	14.95	243	0.0255	0.9925
0.0182	16.0	260	0.0354	0.9850
0.0504	16.98	276	0.0039	1.0
0.0283	17.97	292	0.0199	1.0
0.0241	18.95	308	0.0250	0.9925
0.0268	19.69	320	0.0711	0.9850

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.15.0