|
--- |
|
license: apache-2.0 |
|
base_model: facebook/deit-tiny-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: hushem_conflu_deneme_f1 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: test |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.4222222222222222 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# hushem_conflu_deneme_f1 |
|
|
|
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.1726 |
|
- Accuracy: 0.4222 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 6 | 1.4791 | 0.3333 | |
|
| 2.0372 | 2.0 | 12 | 1.3991 | 0.2444 | |
|
| 2.0372 | 3.0 | 18 | 1.9327 | 0.2444 | |
|
| 1.2524 | 4.0 | 24 | 1.4584 | 0.3556 | |
|
| 1.1547 | 5.0 | 30 | 1.3317 | 0.3556 | |
|
| 1.1547 | 6.0 | 36 | 1.9319 | 0.3333 | |
|
| 0.8748 | 7.0 | 42 | 1.3603 | 0.4222 | |
|
| 0.8748 | 8.0 | 48 | 1.0979 | 0.5333 | |
|
| 0.8902 | 9.0 | 54 | 1.9103 | 0.4222 | |
|
| 0.6653 | 10.0 | 60 | 2.0004 | 0.3778 | |
|
| 0.6653 | 11.0 | 66 | 2.0962 | 0.4 | |
|
| 0.5253 | 12.0 | 72 | 1.2246 | 0.5111 | |
|
| 0.5253 | 13.0 | 78 | 1.6731 | 0.4889 | |
|
| 0.5223 | 14.0 | 84 | 2.1516 | 0.4 | |
|
| 0.2968 | 15.0 | 90 | 2.5065 | 0.4 | |
|
| 0.2968 | 16.0 | 96 | 2.0657 | 0.4444 | |
|
| 0.4394 | 17.0 | 102 | 1.5876 | 0.4667 | |
|
| 0.4394 | 18.0 | 108 | 2.1433 | 0.4 | |
|
| 0.2725 | 19.0 | 114 | 1.4220 | 0.5556 | |
|
| 0.1718 | 20.0 | 120 | 1.7558 | 0.4667 | |
|
| 0.1718 | 21.0 | 126 | 2.3734 | 0.4667 | |
|
| 0.0642 | 22.0 | 132 | 2.9683 | 0.4667 | |
|
| 0.0642 | 23.0 | 138 | 2.9217 | 0.4889 | |
|
| 0.0435 | 24.0 | 144 | 3.4732 | 0.4667 | |
|
| 0.0409 | 25.0 | 150 | 3.8797 | 0.4667 | |
|
| 0.0409 | 26.0 | 156 | 4.3387 | 0.4444 | |
|
| 0.0418 | 27.0 | 162 | 3.9839 | 0.4444 | |
|
| 0.0418 | 28.0 | 168 | 4.5122 | 0.4444 | |
|
| 0.0035 | 29.0 | 174 | 4.2517 | 0.4444 | |
|
| 0.0006 | 30.0 | 180 | 3.9958 | 0.4444 | |
|
| 0.0006 | 31.0 | 186 | 3.9647 | 0.4444 | |
|
| 0.0004 | 32.0 | 192 | 3.9928 | 0.4444 | |
|
| 0.0004 | 33.0 | 198 | 4.0376 | 0.4222 | |
|
| 0.0003 | 34.0 | 204 | 4.0736 | 0.4222 | |
|
| 0.0002 | 35.0 | 210 | 4.1046 | 0.4222 | |
|
| 0.0002 | 36.0 | 216 | 4.1284 | 0.4222 | |
|
| 0.0002 | 37.0 | 222 | 4.1466 | 0.4222 | |
|
| 0.0002 | 38.0 | 228 | 4.1585 | 0.4222 | |
|
| 0.0002 | 39.0 | 234 | 4.1664 | 0.4222 | |
|
| 0.0002 | 40.0 | 240 | 4.1704 | 0.4222 | |
|
| 0.0002 | 41.0 | 246 | 4.1721 | 0.4222 | |
|
| 0.0002 | 42.0 | 252 | 4.1726 | 0.4222 | |
|
| 0.0002 | 43.0 | 258 | 4.1726 | 0.4222 | |
|
| 0.0002 | 44.0 | 264 | 4.1726 | 0.4222 | |
|
| 0.0002 | 45.0 | 270 | 4.1726 | 0.4222 | |
|
| 0.0002 | 46.0 | 276 | 4.1726 | 0.4222 | |
|
| 0.0002 | 47.0 | 282 | 4.1726 | 0.4222 | |
|
| 0.0002 | 48.0 | 288 | 4.1726 | 0.4222 | |
|
| 0.0002 | 49.0 | 294 | 4.1726 | 0.4222 | |
|
| 0.0002 | 50.0 | 300 | 4.1726 | 0.4222 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
