vit-base-patch16-224-in21k

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7692
• F1: 0.9865

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: 2e-05
• train_batch_size: 48
• eval_batch_size: 48
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	10	1.5877	0.6675
No log	2.0	20	1.4149	0.8402
No log	3.0	30	1.2687	0.8917
No log	4.0	40	1.1382	0.9113
No log	5.0	50	1.0214	0.9523
No log	6.0	60	0.9285	0.9662
No log	7.0	70	0.8601	0.9728
No log	8.0	80	0.8089	0.9797
No log	9.0	90	0.7796	0.9865
No log	10.0	100	0.7692	0.9865

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3