swin-tiny-patch4-window7-224-dmae-humeda-muestra

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9468
• Accuracy: 0.6538

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	0.8421	4	1.4539	0.5385
No log	1.8947	9	1.3377	0.4615
1.4928	2.9474	14	1.1130	0.6154
1.4928	4.0	19	1.0588	0.5962
1.046	4.8421	23	1.0164	0.6346
1.046	5.8947	28	0.9468	0.6538
0.8537	6.9474	33	0.9437	0.6346
0.8537	8.0	38	0.9538	0.5962
0.749	8.4211	40	0.9551	0.5962

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1