metadata
license: apache-2.0
base_model: microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Balanced-No-Augmentation-swinv2-base
results: []
Balanced-No-Augmentation-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: 3.6109
- Accuracy: 0.5692
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: 16
- total_train_batch_size: 256
- 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 |
|---|---|---|---|---|
| 2.2985 | 0.98 | 11 | 1.4531 | 0.4822 |
| 0.9081 | 1.97 | 22 | 1.5086 | 0.5731 |
| 0.4604 | 2.95 | 33 | 1.9810 | 0.5692 |
| 0.2255 | 3.93 | 44 | 3.0618 | 0.5415 |
| 0.1339 | 4.92 | 55 | 2.8634 | 0.5613 |
| 0.0883 | 5.99 | 67 | 3.0244 | 0.5652 |
| 0.0605 | 6.97 | 78 | 3.5175 | 0.5573 |
| 0.0506 | 7.96 | 89 | 3.4068 | 0.5850 |
| 0.0272 | 8.94 | 100 | 3.6996 | 0.5573 |
| 0.0262 | 9.83 | 110 | 3.6109 | 0.5692 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2