|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swinv2-tiny-patch4-window8-256 |
|
tags: |
|
- image-classification |
|
- vision |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: swinv2-tiny-patch4-window8-256-finetuned-galaxy10-decals |
|
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. --> |
|
|
|
# swinv2-tiny-patch4-window8-256-finetuned-galaxy10-decals |
|
|
|
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the matthieulel/galaxy10_decals dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4357 |
|
- Accuracy: 0.8585 |
|
|
|
## 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: 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: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| 1.318 | 0.9940 | 124 | 1.0409 | 0.6359 | |
|
| 0.9268 | 1.9960 | 249 | 0.7164 | 0.7497 | |
|
| 0.8221 | 2.9980 | 374 | 0.6210 | 0.7875 | |
|
| 0.7276 | 4.0 | 499 | 0.5564 | 0.8162 | |
|
| 0.6425 | 4.9940 | 623 | 0.5226 | 0.8162 | |
|
| 0.6518 | 5.9960 | 748 | 0.5377 | 0.8185 | |
|
| 0.6096 | 6.9980 | 873 | 0.5341 | 0.8219 | |
|
| 0.6282 | 8.0 | 998 | 0.4718 | 0.8399 | |
|
| 0.5394 | 8.9940 | 1122 | 0.5113 | 0.8281 | |
|
| 0.5718 | 9.9960 | 1247 | 0.5019 | 0.8292 | |
|
| 0.5507 | 10.9980 | 1372 | 0.4545 | 0.8461 | |
|
| 0.4921 | 12.0 | 1497 | 0.4613 | 0.8416 | |
|
| 0.5571 | 12.9940 | 1621 | 0.4587 | 0.8416 | |
|
| 0.512 | 13.9960 | 1746 | 0.4673 | 0.8512 | |
|
| 0.4855 | 14.9980 | 1871 | 0.4641 | 0.8489 | |
|
| 0.4895 | 16.0 | 1996 | 0.4556 | 0.8450 | |
|
| 0.4809 | 16.9940 | 2120 | 0.4317 | 0.8523 | |
|
| 0.4785 | 17.9960 | 2245 | 0.4338 | 0.8534 | |
|
| 0.444 | 18.9980 | 2370 | 0.4357 | 0.8579 | |
|
| 0.4255 | 19.8798 | 2480 | 0.4357 | 0.8585 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 1.12.1+cu116 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|