art_classifier

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: 0.7972
• Accuracy: 0.7692

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8	2	1.0677	0.5128
No log	2.0	5	0.9809	0.6667
No log	2.8	7	0.9331	0.6410
0.9889	4.0	10	0.8836	0.6667
0.9889	4.8	12	0.8566	0.7436
0.9889	6.0	15	0.8382	0.7179
0.9889	6.8	17	0.8205	0.7692
0.774	8.0	20	0.7972	0.7692

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1
• Datasets 2.15.0
• Tokenizers 0.15.0