flower_classifier

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

• Loss: 0.2238
• Accuracy: 0.9878

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: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0568	1.0	102	0.9734	0.9322
0.3193	2.0	205	0.3169	0.9805
0.1862	2.99	306	0.2250	0.9853

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3