0.50-200Train-100Test-vit-base

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

• Loss: 0.7055
• Accuracy: 0.8140

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
1.9228	0.9931	36	1.4677	0.5921
0.5728	1.9862	72	0.7717	0.7721
0.2216	2.9793	108	0.6836	0.7930
0.052	4.0	145	0.6623	0.8052
0.0145	4.9931	181	0.7002	0.7991
0.0075	5.9862	217	0.6851	0.8131
0.0059	6.9793	253	0.6920	0.8166
0.0045	8.0	290	0.6996	0.8140
0.004	8.9931	326	0.7044	0.8140
0.0042	9.9310	360	0.7055	0.8140

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1