metadata
license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: S1_M1_R2_swint_42509598
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: 0.9983217453847998
S1_M1_R2_swint_42509598
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0089
- Accuracy: 0.9983
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0211 | 1.0 | 260 | 0.0173 | 0.9954 |
| 0.0208 | 2.0 | 521 | 0.0103 | 0.9969 |
| 0.009 | 3.0 | 782 | 0.0159 | 0.9964 |
| 0.0062 | 4.0 | 1043 | 0.0091 | 0.9983 |
| 0.0002 | 4.99 | 1300 | 0.0089 | 0.9983 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.11.0+cu102
- Datasets 2.16.0
- Tokenizers 0.15.0