swin-tiny-patch4-window7-224-mulder-v-scully-colab2

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: 0.5344
• Accuracy: 1.0

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	1.0	1	0.6899	0.5
No log	2.0	2	0.6701	0.25
No log	3.0	3	0.6309	0.5
No log	4.0	4	0.6049	0.5
No log	5.0	5	0.5828	0.5
No log	6.0	6	0.5650	0.75
No log	7.0	7	0.5486	0.75
No log	8.0	8	0.5344	1.0
No log	9.0	9	0.5240	1.0
0.2978	10.0	10	0.5149	1.0
0.2978	11.0	11	0.5066	1.0
0.2978	12.0	12	0.4980	1.0
0.2978	13.0	13	0.4880	1.0
0.2978	14.0	14	0.4699	1.0
0.2978	15.0	15	0.4507	1.0
0.2978	16.0	16	0.4310	1.0
0.2978	17.0	17	0.4155	1.0
0.2978	18.0	18	0.4054	1.0
0.2978	19.0	19	0.3994	1.0
0.1751	20.0	20	0.3970	1.0

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3