<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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
