metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/swin-base-patch4-window12-384
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: SwimV1Base
results: []
SwimV1Base
This model is a fine-tuned version of microsoft/swin-base-patch4-window12-384 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0041
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 |
|---|---|---|---|
| 0.2296 | 1.0 | 77 | 0.0181 |
| 0.1378 | 2.0 | 154 | 0.0063 |
| 0.0940 | 3.0 | 231 | 0.1362 |
| 0.0890 | 4.0 | 308 | 0.0164 |
| 0.0590 | 5.0 | 385 | 0.0008 |
| 0.0474 | 6.0 | 462 | 0.0347 |
| 0.0558 | 7.0 | 539 | 0.0344 |
| 0.0430 | 8.0 | 616 | 0.0121 |
| 0.0198 | 9.0 | 693 | 0.0017 |
| 0.0086 | 10.0 | 770 | 0.0041 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1