1_M_cards-swinv2-base-patch4-window12to16-192to256-22kto1k-ft-finetuned-v3

This model is a fine-tuned version of microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1701
• Accuracy: 0.5118

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: 128
• eval_batch_size: 128
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• 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
1.3156	0.9995	1633	1.2976	0.4477
1.2943	1.9997	3267	1.2443	0.4668
1.2411	2.9998	4901	1.2229	0.4787
1.2368	4.0	6535	1.1967	0.4901
1.1973	4.9995	8168	1.1910	0.4927
1.2124	5.9997	9802	1.1811	0.4989
1.1753	6.9998	11436	1.1685	0.5062
1.1554	8.0	13070	1.1681	0.5080
1.1279	8.9995	14703	1.1685	0.5100
1.1121	9.9954	16330	1.1701	0.5118

Framework versions

• Transformers 4.41.0
• Pytorch 2.0.1+cu117
• Datasets 2.19.1
• Tokenizers 0.19.1