condition-Kitchen

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1685
• Rmse: 1.0810

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: 0.0002
• 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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse
No log	1.0	101	1.2101	1.1001
No log	2.0	202	0.7917	0.8898
No log	3.0	303	1.0430	1.0213
No log	4.0	404	0.9290	0.9639
2.8472	5.0	505	0.6923	0.8321
2.8472	6.0	606	0.8079	0.8989
2.8472	7.0	707	0.7159	0.8461
2.8472	8.0	808	0.6934	0.8327

Framework versions

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