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

Loss: 0.2998
Accuracy: 0.8771

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
0.887	1.0	19	0.4012	0.8566
0.4302	2.0	38	0.3361	0.8656
0.3477	3.0	57	0.3272	0.8656
0.3281	4.0	76	0.3129	0.8694
0.308	5.0	95	0.2984	0.8732
0.2821	6.0	114	0.3010	0.8694
0.2763	7.0	133	0.2998	0.8771
0.2607	8.0	152	0.2938	0.8720
0.2502	9.0	171	0.2990	0.8732
0.2337	10.0	190	0.2978	0.8758

Framework versions

Transformers 4.43.3
Pytorch 1.13.1+cu117
Datasets 2.20.0
Tokenizers 0.19.1

djbp/swin-base-patch4-window7-224-MM_Classification_base

swin-base-patch4-window7-224-MM_Classification_base

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

djbp/
swin-base-patch4-window7-224-MM_Classification_base