metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: SwimV2
results: []
SwimV2
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: 0.0290
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2588 | 1.0 | 77 | 0.0491 |
| 0.1207 | 2.0 | 154 | 0.0314 |
| 0.1638 | 3.0 | 231 | 0.0820 |
| 0.0741 | 4.0 | 308 | 0.0300 |
| 0.0911 | 5.0 | 385 | 0.0147 |
| 0.0837 | 6.0 | 462 | 0.0227 |
| 0.0634 | 7.0 | 539 | 0.0381 |
| 0.0497 | 8.0 | 616 | 0.0427 |
| 0.0371 | 9.0 | 693 | 0.0250 |
| 0.0345 | 10.0 | 770 | 0.0290 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2