metadata
license: apache-2.0
base_model: microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Train-Augmentation-V2-swinv2-base
results: []
Train-Augmentation-V2-swinv2-base
This model is a fine-tuned version of microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9822
- Accuracy: 0.8459
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5894 | 0.99 | 109 | 0.7123 | 0.7481 |
| 0.2772 | 2.0 | 219 | 0.6394 | 0.7970 |
| 0.1863 | 3.0 | 329 | 0.7819 | 0.7669 |
| 0.0925 | 4.0 | 439 | 0.7062 | 0.8083 |
| 0.0461 | 4.99 | 548 | 0.8637 | 0.8120 |
| 0.0427 | 6.0 | 658 | 0.9080 | 0.7970 |
| 0.043 | 7.0 | 768 | 1.0747 | 0.8045 |
| 0.0074 | 8.0 | 878 | 0.9019 | 0.8421 |
| 0.0169 | 8.99 | 987 | 0.9099 | 0.8459 |
| 0.015 | 10.0 | 1097 | 0.9512 | 0.8647 |
| 0.0022 | 11.0 | 1207 | 1.0051 | 0.8609 |
| 0.0081 | 12.0 | 1317 | 1.0061 | 0.8308 |
| 0.0013 | 12.99 | 1426 | 0.9844 | 0.8534 |
| 0.0037 | 14.0 | 1536 | 0.9864 | 0.8459 |
| 0.0002 | 14.9 | 1635 | 0.9822 | 0.8459 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2