dental_classification_model_010424_1

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: 0.5468
• Accuracy: 0.8293

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.9173	0.99	41	1.9026	0.2825
1.7055	2.0	83	1.6619	0.3882
1.5398	2.99	124	1.5061	0.4849
1.3415	4.0	166	1.3317	0.5801
1.1753	4.99	207	1.2437	0.5876
1.017	6.0	249	1.1052	0.6390
0.8724	6.99	290	0.9521	0.6873
0.8207	8.0	332	0.9114	0.7115
0.7706	8.99	373	0.8574	0.7130
0.6788	10.0	415	0.7974	0.7523
0.63	10.99	456	0.7611	0.7659
0.5633	12.0	498	0.7764	0.7553
0.5581	12.99	539	0.7370	0.7779
0.5117	14.0	581	0.6945	0.7689
0.4933	14.99	622	0.7066	0.7719
0.4787	16.0	664	0.6405	0.8006
0.4169	16.99	705	0.6443	0.8036
0.3756	18.0	747	0.5991	0.8187
0.3629	18.99	788	0.5774	0.8202
0.3719	20.0	830	0.5451	0.8369
0.4216	20.99	871	0.5623	0.8338
0.3739	22.0	913	0.5995	0.8066
0.3096	22.99	954	0.5330	0.8353
0.3002	24.0	996	0.5109	0.8323
0.3372	24.99	1037	0.5468	0.8293

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2