Docty/Mangovariety

mango_output12

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

• Loss: 0.3909
• Accuracy: 0.9917

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 1337
• 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: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	85	1.2826	0.9375
No log	2.0	170	0.7519	0.975
No log	3.0	255	0.5236	0.9792
No log	4.0	340	0.4190	0.9875
No log	5.0	425	0.3909	0.9917

Framework versions

• Transformers 4.51.1
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0