vit-animals

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the mertcobanov/animals dataset. It achieves the following results on the evaluation set:

• Loss: 0.2444
• Accuracy: 0.9565

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: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.9211	0.4926	100	2.8644	0.8963
1.7472	0.9852	200	1.6272	0.9380
0.6862	1.4778	300	0.7584	0.9519
0.3567	1.9704	400	0.4741	0.9519
0.167	2.4631	500	0.3281	0.9546
0.1162	2.9557	600	0.2864	0.9565
0.0915	3.4483	700	0.2587	0.9528
0.0847	3.9409	800	0.2444	0.9565

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0
• Datasets 3.5.0
• Tokenizers 0.21.1