<!-- 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. -->
swinv2_largeFunny3
This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12-192-22k on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6566
- Accuracy: 0.6954
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6918 | 0.55 | 100 | 0.6507 | 0.6218 |
| 0.4992 | 1.09 | 200 | 0.6430 | 0.6134 |
| 0.5334 | 1.64 | 300 | 0.6240 | 0.6702 |
| 0.4006 | 2.19 | 400 | 0.6579 | 0.6660 |
| 0.4454 | 2.73 | 500 | 0.6503 | 0.6891 |
| 0.2833 | 3.28 | 600 | 0.6518 | 0.6912 |
| 0.2447 | 3.83 | 700 | 0.6566 | 0.6954 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
