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-finetuned-mgasior-2024
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: 0.3228346456692913
swin-tiny-patch4-window7-224-finetuned-mgasior-2024
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: 1.6359
- Accuracy: 0.3228
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: 0.005
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 9 | 1.6990 | 0.2283 |
| 1.7601 | 2.0 | 18 | 5.0280 | 0.1654 |
| 1.774 | 3.0 | 27 | 1.6553 | 0.3228 |
| 1.7759 | 4.0 | 36 | 1.6896 | 0.3228 |
| 1.6705 | 5.0 | 45 | 1.6497 | 0.3228 |
| 1.7113 | 6.0 | 54 | 1.6426 | 0.3228 |
| 1.6718 | 7.0 | 63 | 1.6391 | 0.3228 |
| 1.6606 | 8.0 | 72 | 1.6359 | 0.3228 |
Framework versions
- Transformers 4.36.1
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0