metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification
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: 0.3924731182795699
swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.0567
- Accuracy: 0.3925
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- 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 |
|---|---|---|---|---|
| No log | 0.8889 | 6 | 2.8975 | 0.1398 |
| 2.9658 | 1.9259 | 13 | 2.6866 | 0.2204 |
| 2.6529 | 2.9630 | 20 | 2.4370 | 0.3011 |
| 2.6529 | 4.0 | 27 | 2.2516 | 0.3495 |
| 2.3311 | 4.8889 | 33 | 2.1685 | 0.3710 |
| 2.1441 | 5.9259 | 40 | 2.0987 | 0.3656 |
| 2.1441 | 6.9630 | 47 | 2.0567 | 0.3925 |
| 2.0507 | 8.0 | 54 | 2.0416 | 0.3871 |
| 1.988 | 8.8889 | 60 | 2.0368 | 0.3763 |
Framework versions
- Transformers 4.41.2
- Pytorch 1.13.1+cu117
- Datasets 2.19.2
- Tokenizers 0.19.1