|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Train-Test-Augmentation-swinv2-base |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Train-Test-Augmentation-swinv2-base |
|
|
|
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7329 |
|
- Accuracy: 0.8206 |
|
|
|
## 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: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.5364 | 0.98 | 23 | 0.8286 | 0.7257 | |
|
| 0.4948 | 1.97 | 46 | 0.6373 | 0.7958 | |
|
| 0.2036 | 2.99 | 70 | 0.5860 | 0.8234 | |
|
| 0.1158 | 3.98 | 93 | 0.6284 | 0.8151 | |
|
| 0.0656 | 4.96 | 116 | 0.6982 | 0.8129 | |
|
| 0.0568 | 5.99 | 140 | 0.7678 | 0.8217 | |
|
| 0.0332 | 6.97 | 163 | 0.7208 | 0.8206 | |
|
| 0.0279 | 8.0 | 187 | 0.7053 | 0.8217 | |
|
| 0.0169 | 8.98 | 210 | 0.7489 | 0.8256 | |
|
| 0.0125 | 9.84 | 230 | 0.7329 | 0.8206 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.2 |
|
|
