metadata
license: apache-2.0
base_model: microsoft/swinv2-base-patch4-window12-192-22k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Train-Test-Augmentation-V3D-swinv2-base
results: []
Train-Test-Augmentation-V3D-swinv2-base
This model is a fine-tuned version of microsoft/swinv2-base-patch4-window12-192-22k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7725
- Accuracy: 0.8142
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 |
|---|---|---|---|---|
| 1.8252 | 0.9825 | 28 | 0.9390 | 0.7273 |
| 0.5282 | 2.0 | 57 | 0.6414 | 0.7804 |
| 0.2556 | 2.9825 | 85 | 0.6210 | 0.7815 |
| 0.1633 | 4.0 | 114 | 0.7030 | 0.8142 |
| 0.0869 | 4.9825 | 142 | 0.7398 | 0.7877 |
| 0.0524 | 6.0 | 171 | 0.8167 | 0.7962 |
| 0.0277 | 6.9825 | 199 | 0.6993 | 0.8176 |
| 0.0245 | 8.0 | 228 | 0.7444 | 0.8210 |
| 0.0232 | 8.9825 | 256 | 0.8129 | 0.8142 |
| 0.017 | 9.8246 | 280 | 0.7725 | 0.8142 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1