vit-base-patch16-224-9models

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: 0.0167
• Accuracy: 0.9959

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: 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
0.5952	0.9790	35	0.2206	0.9344
0.1228	1.9860	71	0.0889	0.9754
0.1133	2.9930	107	0.0701	0.9816
0.0877	4.0	143	0.0808	0.9754
0.0597	4.9790	178	0.0234	0.9939
0.0718	5.9860	214	0.0325	0.9898
0.0666	6.9930	250	0.0459	0.9836
0.0467	8.0	286	0.0162	0.9959
0.0446	8.9790	321	0.0155	0.9959
0.0391	9.7902	350	0.0167	0.9959

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1