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

Loss: 0.2779
Accuracy: 0.9083
F1 Macro: 0.9081

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: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 8
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
0.7613	1.0	90	0.6598	0.7319	0.7314
0.5505	2.0	180	0.7253	0.7111	0.6945
0.4291	3.0	270	0.4152	0.8472	0.8485
0.4423	4.0	360	0.3808	0.8611	0.8592
0.3619	5.0	450	0.3967	0.8639	0.8616
0.2751	6.0	540	0.3346	0.8889	0.8873
0.2944	7.0	630	0.3226	0.8917	0.8910
0.1867	8.0	720	0.2779	0.9083	0.9081

Framework versions

Transformers 5.12.1
Pytorch 2.11.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

nexusbert/tomato-disease-vit

tomato-disease-vit

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

nexusbert/
tomato-disease-vit