swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification

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

• Loss: 0.4046
• Accuracy: 0.8426

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
0.5809	0.9884	64	0.5024	0.7937
0.5326	1.9923	129	0.4402	0.8132
0.4626	2.9961	194	0.4244	0.8284
0.4778	4.0	259	0.4234	0.8274
0.4109	4.9884	323	0.4197	0.8306
0.3764	5.9923	388	0.4095	0.8295
0.3725	6.9961	453	0.4046	0.8426
0.3583	8.0	518	0.4109	0.8371
0.3451	8.9884	582	0.4171	0.8350
0.3351	9.8842	640	0.4153	0.8404

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1