metadata
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: msi-swinv2-tiny
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6273762929829466
msi-swinv2-tiny
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: 1.5764
- Accuracy: 0.6274
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4392 | 1.0 | 2015 | 0.7935 | 0.6100 |
| 0.3266 | 2.0 | 4031 | 0.9694 | 0.6132 |
| 0.2673 | 3.0 | 6047 | 1.2037 | 0.6114 |
| 0.2222 | 4.0 | 8063 | 1.3734 | 0.6097 |
| 0.1922 | 5.0 | 10078 | 1.3308 | 0.6235 |
| 0.1716 | 6.0 | 12094 | 1.4758 | 0.6136 |
| 0.1742 | 7.0 | 14110 | 1.4332 | 0.6274 |
| 0.1653 | 8.0 | 16126 | 1.4940 | 0.6247 |
| 0.1429 | 9.0 | 18141 | 1.6058 | 0.6236 |
| 0.1546 | 10.0 | 20150 | 1.5764 | 0.6274 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0