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

Loss: 0.5135
Accuracy: 0.8337

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: 0.0003
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0366	1.0	400	0.9471	0.72
0.8257	2.0	800	0.7889	0.7538
0.7119	3.0	1200	0.7232	0.7775
0.6969	4.0	1600	0.6739	0.7837
0.6487	5.0	2000	0.6371	0.7863
0.5956	6.0	2400	0.6198	0.7887
0.5604	7.0	2800	0.5941	0.8025
0.5732	8.0	3200	0.5867	0.795
0.5578	9.0	3600	0.5705	0.8025
0.5449	10.0	4000	0.5575	0.8113
0.5419	11.0	4400	0.5505	0.8213
0.5086	12.0	4800	0.5385	0.8213
0.4929	13.0	5200	0.5340	0.8213
0.4701	14.0	5600	0.5297	0.8187
0.4803	15.0	6000	0.5240	0.8225
0.4988	16.0	6400	0.5197	0.83
0.4842	17.0	6800	0.5165	0.8313
0.4917	18.0	7200	0.5148	0.8313
0.4734	19.0	7600	0.5140	0.8325
0.4714	20.0	8000	0.5135	0.8337

Framework versions

Transformers 4.45.2
Pytorch 2.4.1+cpu
Datasets 3.0.1
Tokenizers 0.20.1

cvmil/swin-base-patch4-window7-224-augmented

swin-base-patch4-window7-224_11092024

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

cvmil/
swin-base-patch4-window7-224-augmented