metadata
license: apache-2.0
base_model: microsoft/swinv2-small-patch4-window16-256
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Boya1_RMSProp_1-e5_10Epoch_swinv2-small-patch4-window16-256_fold4
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6754267136277432
Boya1_RMSProp_1-e5_10Epoch_swinv2-small-patch4-window16-256_fold4
This model is a fine-tuned version of microsoft/swinv2-small-patch4-window16-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0810
- Accuracy: 0.6754
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|---|
| 1.0464 | 1.0 | 1847 | 1.2439 | 0.5787 |
| 1.0687 | 2.0 | 3694 | 1.0750 | 0.6291 |
| 0.9704 | 3.0 | 5541 | 1.0613 | 0.6424 |
| 1.0466 | 4.0 | 7388 | 0.9934 | 0.6554 |
| 0.8838 | 5.0 | 9235 | 0.9961 | 0.6719 |
| 0.772 | 6.0 | 11082 | 1.0164 | 0.6689 |
| 0.5504 | 7.0 | 12929 | 1.0391 | 0.6776 |
| 0.4673 | 8.0 | 14776 | 1.0527 | 0.6768 |
| 0.4832 | 9.0 | 16623 | 1.0764 | 0.6733 |
| 0.5907 | 10.0 | 18470 | 1.0810 | 0.6754 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.1.0
- Datasets 2.19.0
- Tokenizers 0.19.1