ViT_Cucumber

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

• Loss: 0.0155
• Accuracy: 0.9976

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1694	0.3571	100	0.1965	0.9607
0.1409	0.7143	200	0.2409	0.9261
0.1024	1.0714	300	0.0903	0.9780
0.0326	1.4286	400	0.0630	0.9866
0.0338	1.7857	500	0.0675	0.9843
0.0082	2.1429	600	0.0508	0.9882
0.0072	2.5	700	0.0609	0.9874
0.0056	2.8571	800	0.0175	0.9976
0.0044	3.2143	900	0.0154	0.9976
0.0042	3.5714	1000	0.0151	0.9976
0.0045	3.9286	1100	0.0155	0.9976

Framework versions

• Transformers 4.44.2
• Pytorch 2.3.0+cu118
• Datasets 3.2.0
• Tokenizers 0.19.1