vit-base-patch16-224-perros-y-gatos

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: 0.1577
• Accuracy: 1.0

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• 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	0.8889	6	0.6543	0.5789
0.5484	1.9259	13	0.3385	0.8421
0.5484	2.9630	20	0.2123	0.9474
0.2164	4.0	27	0.1577	1.0
0.2164	4.8889	33	0.1404	1.0
0.1367	5.9259	40	0.1375	0.9474
0.1367	6.9630	47	0.1312	1.0
0.1155	8.0	54	0.1140	1.0
0.0878	8.8889	60	0.1107	1.0

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1