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: 0.3652
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	0.6105	0.75
No log	2.0	2	0.6975	0.5
No log	3.0	3	0.8309	0.25
No log	4.0	4	0.7604	0.5
No log	5.0	5	0.6327	0.5
No log	6.0	6	0.5101	0.75
No log	7.0	7	0.4148	0.75
No log	8.0	8	0.3652	1.0
No log	9.0	9	0.3433	1.0
0.0984	10.0	10	0.3231	1.0
0.0984	11.0	11	0.3071	1.0
0.0984	12.0	12	0.3047	1.0
0.0984	13.0	13	0.3189	0.75
0.0984	14.0	14	0.3437	0.75
0.0984	15.0	15	0.3701	0.75
0.0984	16.0	16	0.3959	0.75
0.0984	17.0	17	0.4167	0.75
0.0984	18.0	18	0.4190	0.75
0.0984	19.0	19	0.4154	0.75
0.0632	20.0	20	0.4114	0.75

Framework versions

Transformers 4.28.0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3

dvs/swin-tiny-patch4-window7-224-mulder-v-scully-colab

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

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

dvs/
swin-tiny-patch4-window7-224-mulder-v-scully-colab