Patacognition
Collection
All ViTs, datasets and spaces created for the sole purpose of patacón recognition.
•
8 items
•
Updated
patacoswin
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0203
- Accuracy: 1.0
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.96 | 6 | 0.4003 | 0.875 |
| 0.5091 | 1.92 | 12 | 0.1308 | 0.9886 |
| 0.5091 | 2.88 | 18 | 0.0522 | 0.9886 |
| 0.1585 | 4.0 | 25 | 0.0203 | 1.0 |
| 0.0925 | 4.96 | 31 | 0.0156 | 1.0 |
| 0.0925 | 5.92 | 37 | 0.0196 | 1.0 |
| 0.0539 | 6.88 | 43 | 0.0095 | 1.0 |
| 0.0397 | 8.0 | 50 | 0.0089 | 1.0 |
| 0.0397 | 8.96 | 56 | 0.0089 | 1.0 |
| 0.0378 | 9.6 | 60 | 0.0090 | 1.0 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.