|
--- |
|
license: apache-2.0 |
|
base_model: facebook/deit-tiny-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: smids_5x_deit_tiny_sgd_0001_fold4 |
|
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: 0.8 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# smids_5x_deit_tiny_sgd_0001_fold4 |
|
|
|
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: 0.4936 |
|
- Accuracy: 0.8 |
|
|
|
## 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: 0.0001 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 1.1564 | 1.0 | 375 | 1.1576 | 0.3767 | |
|
| 1.0853 | 2.0 | 750 | 1.0913 | 0.4 | |
|
| 0.9971 | 3.0 | 1125 | 1.0409 | 0.44 | |
|
| 0.9972 | 4.0 | 1500 | 0.9979 | 0.4683 | |
|
| 0.9211 | 5.0 | 1875 | 0.9595 | 0.4967 | |
|
| 0.885 | 6.0 | 2250 | 0.9224 | 0.535 | |
|
| 0.8576 | 7.0 | 2625 | 0.8878 | 0.5583 | |
|
| 0.8551 | 8.0 | 3000 | 0.8542 | 0.5783 | |
|
| 0.8253 | 9.0 | 3375 | 0.8221 | 0.6017 | |
|
| 0.8198 | 10.0 | 3750 | 0.7908 | 0.6283 | |
|
| 0.6752 | 11.0 | 4125 | 0.7615 | 0.645 | |
|
| 0.6508 | 12.0 | 4500 | 0.7343 | 0.6767 | |
|
| 0.6556 | 13.0 | 4875 | 0.7097 | 0.69 | |
|
| 0.7132 | 14.0 | 5250 | 0.6866 | 0.7083 | |
|
| 0.6057 | 15.0 | 5625 | 0.6661 | 0.7183 | |
|
| 0.5722 | 16.0 | 6000 | 0.6478 | 0.7283 | |
|
| 0.5982 | 17.0 | 6375 | 0.6328 | 0.7333 | |
|
| 0.5686 | 18.0 | 6750 | 0.6177 | 0.735 | |
|
| 0.5939 | 19.0 | 7125 | 0.6046 | 0.7417 | |
|
| 0.5225 | 20.0 | 7500 | 0.5938 | 0.7483 | |
|
| 0.5314 | 21.0 | 7875 | 0.5829 | 0.7567 | |
|
| 0.5367 | 22.0 | 8250 | 0.5746 | 0.765 | |
|
| 0.506 | 23.0 | 8625 | 0.5665 | 0.77 | |
|
| 0.5218 | 24.0 | 9000 | 0.5589 | 0.7717 | |
|
| 0.5608 | 25.0 | 9375 | 0.5520 | 0.7767 | |
|
| 0.5255 | 26.0 | 9750 | 0.5459 | 0.78 | |
|
| 0.5248 | 27.0 | 10125 | 0.5406 | 0.78 | |
|
| 0.496 | 28.0 | 10500 | 0.5353 | 0.78 | |
|
| 0.4514 | 29.0 | 10875 | 0.5308 | 0.785 | |
|
| 0.4878 | 30.0 | 11250 | 0.5266 | 0.785 | |
|
| 0.4791 | 31.0 | 11625 | 0.5226 | 0.785 | |
|
| 0.4601 | 32.0 | 12000 | 0.5192 | 0.785 | |
|
| 0.527 | 33.0 | 12375 | 0.5161 | 0.7867 | |
|
| 0.4682 | 34.0 | 12750 | 0.5130 | 0.785 | |
|
| 0.4268 | 35.0 | 13125 | 0.5104 | 0.7917 | |
|
| 0.4602 | 36.0 | 13500 | 0.5080 | 0.795 | |
|
| 0.4456 | 37.0 | 13875 | 0.5057 | 0.7983 | |
|
| 0.4657 | 38.0 | 14250 | 0.5038 | 0.7983 | |
|
| 0.5191 | 39.0 | 14625 | 0.5021 | 0.7983 | |
|
| 0.5029 | 40.0 | 15000 | 0.5005 | 0.8 | |
|
| 0.4811 | 41.0 | 15375 | 0.4991 | 0.8 | |
|
| 0.4466 | 42.0 | 15750 | 0.4979 | 0.8 | |
|
| 0.4615 | 43.0 | 16125 | 0.4969 | 0.8017 | |
|
| 0.4147 | 44.0 | 16500 | 0.4960 | 0.8 | |
|
| 0.4484 | 45.0 | 16875 | 0.4953 | 0.8 | |
|
| 0.4471 | 46.0 | 17250 | 0.4947 | 0.8 | |
|
| 0.4839 | 47.0 | 17625 | 0.4942 | 0.8 | |
|
| 0.4773 | 48.0 | 18000 | 0.4939 | 0.8 | |
|
| 0.4334 | 49.0 | 18375 | 0.4937 | 0.8 | |
|
| 0.4329 | 50.0 | 18750 | 0.4936 | 0.8 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.2 |
|
|