condition-Kitchen-swin

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 16.3647
• Rmse: 4.0453

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse
No log	1.0	94	17.9745	4.2396
No log	2.0	188	2.1129	1.4536
No log	3.0	282	1.6826	1.2972
No log	4.0	376	1.2371	1.1122
No log	5.0	470	0.8900	0.9434
6.7108	6.0	564	0.8675	0.9314
6.7108	7.0	658	0.8017	0.8954
6.7108	8.0	752	0.7732	0.8793
6.7108	9.0	846	0.7645	0.8743
6.7108	10.0	940	0.7504	0.8663

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+cu117
• Datasets 2.10.0
• Tokenizers 0.13.0