metadata
license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swin-base-patch4-window7-224-fruits-360-16-7
results: []
swin-base-patch4-window7-224-fruits-360-16-7
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0010
- Accuracy: 0.9998
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0631 | 1.0 | 1057 | 0.0149 | 0.9956 |
| 0.0254 | 2.0 | 2115 | 0.0042 | 0.9986 |
| 0.026 | 3.0 | 3173 | 0.0021 | 0.9990 |
| 0.0092 | 4.0 | 4231 | 0.0035 | 0.9986 |
| 0.0151 | 5.0 | 5288 | 0.0014 | 0.9997 |
| 0.0075 | 6.0 | 6346 | 0.0047 | 0.9989 |
| 0.0001 | 7.0 | 7399 | 0.0010 | 0.9998 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1