metadata
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swinv2-tiny-patch4-window8-256-finalterm
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.89375
swinv2-tiny-patch4-window8-256-finalterm
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3096
- Accuracy: 0.8938
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3728 | 1.0 | 10 | 1.2644 | 0.5156 |
| 1.1308 | 2.0 | 20 | 0.8816 | 0.625 |
| 0.8721 | 3.0 | 30 | 0.6829 | 0.7063 |
| 0.6919 | 4.0 | 40 | 0.5298 | 0.8063 |
| 0.5876 | 5.0 | 50 | 0.4100 | 0.8688 |
| 0.5504 | 6.0 | 60 | 0.4153 | 0.8531 |
| 0.459 | 7.0 | 70 | 0.3828 | 0.8594 |
| 0.4501 | 8.0 | 80 | 0.3941 | 0.8625 |
| 0.4312 | 9.0 | 90 | 0.3650 | 0.8719 |
| 0.4119 | 10.0 | 100 | 0.3515 | 0.875 |
| 0.4014 | 11.0 | 110 | 0.3110 | 0.8969 |
| 0.3896 | 12.0 | 120 | 0.3030 | 0.9031 |
| 0.3822 | 13.0 | 130 | 0.3473 | 0.8812 |
| 0.3985 | 14.0 | 140 | 0.3288 | 0.8875 |
| 0.3826 | 15.0 | 150 | 0.2925 | 0.9 |
| 0.3716 | 16.0 | 160 | 0.3619 | 0.875 |
| 0.365 | 17.0 | 170 | 0.2941 | 0.9 |
| 0.3379 | 18.0 | 180 | 0.3239 | 0.8844 |
| 0.3365 | 19.0 | 190 | 0.3260 | 0.8906 |
| 0.3429 | 20.0 | 200 | 0.3096 | 0.8938 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1