swin-tiny-patch4-window7-224-finetuned-student_six_classes-finetuned-student_six_classes

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

• Loss: 0.4176
• Accuracy: 0.83

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9231	3	0.4943	0.78
No log	1.8462	6	0.4716	0.78
No log	2.7692	9	0.4725	0.81
0.3732	4.0	13	0.4678	0.78
0.3732	4.9231	16	0.4779	0.78
0.3732	5.8462	19	0.4564	0.79
0.3459	6.7692	22	0.4556	0.82
0.3459	8.0	26	0.4757	0.77
0.3459	8.9231	29	0.4773	0.77
0.3273	9.8462	32	0.4661	0.77
0.3273	10.7692	35	0.4518	0.79
0.3273	12.0	39	0.4405	0.81
0.2974	12.9231	42	0.4359	0.82
0.2974	13.8462	45	0.4298	0.82
0.2974	14.7692	48	0.4242	0.84
0.2874	16.0	52	0.4199	0.84
0.2874	16.9231	55	0.4185	0.83
0.2874	17.8462	58	0.4179	0.83
0.2737	18.4615	60	0.4176	0.83

Framework versions

• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1