swinv2-tiny-patch4-window8-256-dmae-humeda-1

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3549
• Accuracy: 0.5

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	1.0	2	1.5476	0.3462
No log	2.0	4	1.4060	0.4615
No log	3.0	6	1.4222	0.4423
No log	4.0	8	1.4011	0.4231
1.4158	5.0	10	1.3764	0.4615
1.4158	6.0	12	1.3549	0.5
1.4158	7.0	14	1.3302	0.5
1.4158	8.0	16	1.3073	0.5
1.4158	9.0	18	1.2923	0.5
1.2817	10.0	20	1.2863	0.5

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1