bridalMakeupClassifier_binary

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: 0.0072
• Accuracy: 1.0
• Precision: 1.0
• Recall: 1.0
• F1: 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	Precision	Recall	F1
0.2966	1.0	23	0.1290	0.9662	0.9432	0.9326	0.9379
0.1233	2.0	46	0.0407	0.9877	0.9670	0.9888	0.9778
0.0469	3.0	69	0.0594	0.9815	0.9368	1.0	0.9674
0.0394	4.0	92	0.0557	0.9877	0.9670	0.9888	0.9778
0.0909	5.0	115	0.0401	0.9908	0.9674	1.0	0.9834
0.05	6.0	138	0.0252	0.9877	0.9670	0.9888	0.9778
0.0451	7.0	161	0.0279	0.9877	0.9885	0.9663	0.9773
0.0231	8.0	184	0.0278	0.9938	0.9780	1.0	0.9889
0.0404	9.0	207	0.0256	0.9877	0.9775	0.9775	0.9775
0.0297	10.0	230	0.0260	0.9908	0.9778	0.9888	0.9832
0.0327	11.0	253	0.0230	0.9938	0.9780	1.0	0.9889
0.0221	12.0	276	0.0140	0.9969	0.9889	1.0	0.9944
0.0294	13.0	299	0.0106	0.9969	0.9889	1.0	0.9944
0.0292	14.0	322	0.0132	0.9969	0.9889	1.0	0.9944
0.0064	15.0	345	0.0231	0.9908	0.9674	1.0	0.9834
0.02	16.0	368	0.0087	0.9969	0.9889	1.0	0.9944
0.0356	17.0	391	0.0114	0.9969	0.9889	1.0	0.9944
0.0232	18.0	414	0.0072	1.0	1.0	1.0	1.0
0.0351	19.0	437	0.0087	0.9969	0.9889	1.0	0.9944
0.0155	20.0	460	0.0075	0.9969	0.9889	1.0	0.9944

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.20.0