beans_no_aug_freeze_tens

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

• Loss: 0.4175
• Accuracy: 0.8872

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: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	65	0.6381	0.8271
0.8113	2.0	130	0.4886	0.8571
0.8113	3.0	195	0.4306	0.8722
0.5137	4.0	260	0.4175	0.8872

Framework versions

• Transformers 4.38.2
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.15.2