metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: condition-Kitchen
results: []
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: 3.5140
- Rmse: 1.8746
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|---|---|---|---|---|
| No log | 1.0 | 134 | 3.5140 | 1.8746 |
| No log | 2.0 | 268 | 1.6198 | 1.2727 |
| No log | 3.0 | 402 | 0.9386 | 0.9688 |
| 8.1621 | 4.0 | 536 | 0.8200 | 0.9056 |
| 8.1621 | 5.0 | 670 | 0.7409 | 0.8607 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.0
- Tokenizers 0.13.0