beans-leaf-disease-detection

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:

• Loss: 0.0404
• Accuracy: 0.9925
• Precision: 0.9926
• Recall: 0.9925
• F1: 0.9925

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 8
• 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: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0492	0.7692	50	0.1117	0.9774	0.9776	0.9774	0.9774
0.0432	1.5385	100	0.1428	0.9624	0.9650	0.9624	0.9620
0.0119	2.3077	150	0.0736	0.9850	0.9851	0.9850	0.9850
0.0038	3.0769	200	0.0404	0.9925	0.9926	0.9925	0.9925
0.0046	3.8462	250	0.0472	0.9850	0.9856	0.9850	0.9850

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1